Advanced search in Research products
Research products
arrow_drop_down
Searching FieldsTerms
Any field
arrow_drop_down
includes
arrow_drop_down
The following results are related to Digital Humanities and Cultural Heritage. Are you interested to view more results? Visit OpenAIRE - Explore.

  • Digital Humanities and Cultural Heritage
  • 2017-2021
  • Publications
  • Other research products
  • Doctoral thesis
  • English

Date (most recent)
arrow_drop_down
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Buriola, Giulia;
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Archivio della ricer...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Archivio della ricer...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Angelini, EMMA PAOLA MARIA VIRGINIA; Grassini, Sabrina; Peters, MANUEL JACQUES HELENA;
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Publications Open Re...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Publications Open Re...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: van Beek, Martinus Josephus Maria;

    This dissertation explores the function of architecture in the illustrated manuscripts of the erudite Spanish Benedictine scholar, artist and preacher Juan Ricci de Guevara. Among architectural historians, Ricci has become famous for his invention of the complete architectural Salomonic order, which has been discussed by modern scholars predominantly isolated from its textual context, and from a formal, aesthetic approach. The new, comprehensive approach of Ricci’s scholarship in the manuscripts shows that he referred to architecture continuously. From this starting point the hypothesis is made that architecture for Ricci was a suitable interdisciplinary agent for his innovative ideas. With architecture, he could establish connections between various sources, methods and arguments, while coincidentally maintaining the scientific level of his scholarly work. This dissertation is the first book in which Ricci’s written oeuvre (which was never published and is now kept in Madrid, El Escorial, the Vatican and Montecassino) is assessed in-depth comprehensively. It results in a detailed insight in his formulation of a pivotal role for architecture and the architectural image in seventeenth-century scholarship, as a result of Ricci’s particular fusion of scholarly, artistic and rhetorical approaches. The recognition of this mechanism results in an updated inventory of his manuscripts, a discussion of important but hitherto unknown sections of the writings in which the position of architecture is discussed and legitimized, an adjustment of the modern formal discussion of the complete Salomonic order, a new analysis of Ricci’s presentation of his ideas to Pope Alexander VII in the 1660s, and the identification of a decoration program by Ricci for the basilica of the abbey of Montecassino.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ NARCIS; Vrije Univer...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    NARCIS
    Doctoral thesis . 2021
    Data sources: NARCIS
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ NARCIS; Vrije Univer...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      NARCIS
      Doctoral thesis . 2021
      Data sources: NARCIS
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: van Beek, M.J.M.;

    This dissertation explores the function of architecture in the illustrated manuscripts of the erudite Spanish Benedictine scholar, artist and preacher Juan Ricci de Guevara. Among architectural historians, Ricci has become famous for his invention of the complete architectural Salomonic order, which has been discussed by modern scholars predominantly isolated from its textual context, and from a formal, aesthetic approach. The new, comprehensive approach of Ricci’s scholarship in the manuscripts shows that he referred to architecture continuously. From this starting point the hypothesis is made that architecture for Ricci was a suitable interdisciplinary agent for his innovative ideas. With architecture, he could establish connections between various sources, methods and arguments, while coincidentally maintaining the scientific level of his scholarly work. This dissertation is the first book in which Ricci’s written oeuvre (which was never published and is now kept in Madrid, El Escorial, the Vatican and Montecassino) is assessed in-depth comprehensively. It results in a detailed insight in his formulation of a pivotal role for architecture and the architectural image in seventeenth-century scholarship, as a result of Ricci’s particular fusion of scholarly, artistic and rhetorical approaches. The recognition of this mechanism results in an updated inventory of his manuscripts, a discussion of important but hitherto unknown sections of the writings in which the position of architecture is discussed and legitimized, an adjustment of the modern formal discussion of the complete Salomonic order, a new analysis of Ricci’s presentation of his ideas to Pope Alexander VII in the 1660s, and the identification of a decoration program by Ricci for the basilica of the abbey of Montecassino.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Vrije Universiteit A...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Vrije Universiteit A...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
  • image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
    Authors: Herron, Donald;

    This study is an examination of the evolution of teachers’ in-service education and continuous professional development in Ireland between 1945 and 1995. The purpose is to investigate the evolution and development of in-service policy, its goals, construction, participation, implementation and outcomes. The objectives are to deepen educators’ understanding of the current in-service issues by locating them in their broader temporal context and to extend the range of policy options considered by providing a basis for comparison with past situations. Its focus is the professional development policies and implementation strategies adopted by the Department of Education, the development and pursuit of policy positions among teachers, school management organisations and teacher educators, and the transactions between them in the evolution of in-service education and training of primary teachers in the Republic of Ireland. The in-service policy antecedents of the three decades prior to 1950 are explored to identify contemporary policies and practices and examine what foundations and legacies they contributed to primary teachers’ in-service education and training between 1945-1995. There were three separate primary-level level in-service initiatives in the 1950s and 1960s, one by the teachers’ union, the INTO, another by the Catholic Church and a Department of Education revision of Irish language. The breadth and depth of the curriculum reforms required Inspectorates to change approaches to in-service policy and practices. Comprehensive primary curriculum reform commenced in 1967 and its dissemination was planned by the Department around policy decisions on and coordinated implementation of strategically interrelated features including in-service training. An In-service Steering Committee, established in 1970, attempted to coordinate various institutions’ in-service contributions. The Committee advocated teacher centres, which when established from 1972, created an atmosphere of local optimism. In the absence of adequate resources or Steering Committee agreement on an encompassing in-service plan, an insufficiency of activities ensued which was curtailed by the mid-1970s recession. Dissatisfaction with the consequences of budget cuts resulted in a review of in-service education policies in 1980. The report of the Committee on In-service Education was ignored and its main recommendation, a national in-service agency, was deferred. There was an increase in the quantity of short course but this did not address access, course depth or continuity or address emerging in-service priorities or deficiencies. The decade from 1987 witnessed a period analysis, national policy making and deliberative processes involved in achieving an education policy consensus. In the case of in-service education and in-career development, departmental preferences with regard to structure, prioritisation of curriculum implementation and defining which in-service activities were funded, preceded the policy-making processes. The preferred option was solidified by the conditionality of the funding source, the European Structural Fund. The policy process, stimulated by the 1991 OECD contributions, expanded a departmental conceptualisation of curriculum-focused in-service training to school-focused organisational, staff and teacher professional development.

    image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Research Repository ...arrow_drop_down
    image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
    Research Repository UCD
    Doctoral thesis . 2021
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Research Repository ...arrow_drop_down
      image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
      Research Repository UCD
      Doctoral thesis . 2021
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Gundersen, Ingar Mørkestøl;

    A growing body of climate data points towards a significant climate cooling in the northern hemisphere during the 6th century AD. Linked to multiple explosive volcanic eruptions between AD 536-547, the cooling event is the coldest that has been documented for the last 2000 years and seems to have persisted, to varying degrees, well into the latter half of the 6th century. Several researchers have claimed that the 6th-century cooling must have resulted in extensive crop failure throughout Scandinavia, followed by famine, plagues, and social unrest. One hypothesis suggests that the population of the Scandinavian Peninsula may have been halved as a result. The combination of prolonged cooling and presumed crop failure is often compared to Norse myths about the Fimbulwinter, but critics argue that the Fimbulwinter hypothesis is rife with the uncritical use of climate data, a lack of source criticism and deterministic conclusions. In many ways, the ongoing discourse follows in line with previous discourses in archaeology, revolving around an artificial dichotomy between crisis and continuity. In this thesis, I examine the climatic and archaeological premises for the Fimbulwinter hypothesis and discuss it against developing theoretical frameworks within the environmental humanities. By using vulnerability and resilience as analytical tools, the subsistence and settlement patterns of selected landscapes are analysed against the possibility of crop failure and famine, with emphasis on the Gudbrandsdalen valley and the Lake Mjøsa region in the inlands of eastern Norway. I conclude that climate cooling had the potential to critically impact some areas, while others were seemingly less affected. These results suggest significant regional diversity in the consequences and adaptations in relation to the 6th-century cooling event. The hypothesis of a halving of the population is up for revision, but the crisis narrative still cannot be fully discounted. This thesis is also available in the Zenodo archive: https://doi.org/10.5281/zenodo.5782896

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    ZENODO
    Other literature type . 2021
    License: CC BY
    Data sources: ZENODO
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    ZENODO
    Thesis . 2021
    License: CC BY
    Data sources: Datacite
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    visibility121
    visibilityviews121
    downloaddownloads113
    Powered by Usage counts
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      ZENODO
      Other literature type . 2021
      License: CC BY
      Data sources: ZENODO
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      ZENODO
      Thesis . 2021
      License: CC BY
      Data sources: Datacite
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • Authors: Vorakitphan, Vorakit;

    In recent years, disinformation has become more viral, mainly due to its spread online on social media, leading to potential threatening consequences for the society. Heterogeneous forms of online disinformation are possible, i.e., deliberately manipulated or fabricated content with the intentional aim of creating conspiracy theories, rumours, or misbehaved stances and judgements, for instance, in news articles, and political discourse and debates. One of many instances of online disinformation, and certainly one of the most dangerous ones, is propaganda. This disinformation instance represents an effective but often misleading communication strategy which is employed to promote a certain viewpoint to the audience, for instance in the political context. The need to effectively and automatically identify, classify and understand such phenomenon is becoming a urgent need. In this thesis, I tackle this issue and I propose a fine-grained classification approach of polarized and propagandist text in news articles and political debates. More precisely, as the audience' perceptions are perceived differently depending on the context, the source of information, the audience background and preferences, a discussed topic can deviate or polarize the audience into a partisanship. This thesis firstly investigates such polarization given a use-case in a political scenario using Aspects-Based Sentiment Analysis to verify how extensively these methods can be employed to gain insights from the political posts on social media. The thesis discusses the design and evaluation of a number of techniques in extracting the main features of propagandist text in the area of Natural Language Processing (NLP) where sentiment analysis, persuasion techniques, message simplicity, and ultimately argumentation are proposed and thoroughly investigated. The findings in this thesis show that such features can capture particular characteristics of propaganda in texts. Furthermore, these features are employed to tackle the NLP tasks of propaganda detection and classification through the design and implementation of a neural architecture to classify fine-grained propaganda techniques. The work in this thesis goes beyond the state-of-the-art of current systems for fine-grained propaganda detection and classification. Various Machine Learning approaches ranging from feature-based logistic regression to recent neural architectures have been experimented on standard benchmarks in propaganda detection. As a result, a full pipeline in propaganda detection and classification is presented where the task of detecting the propagandist text snippets obtained .71 F1-score, and the transformer-based architecture obtained an average of .67 F1-score for the task of propaganda technique classification, outperforming the state-of-the-art systems. This pipeline is demonstrated with a proof-of-concept tool called PROTECT. Finally, as a last contribution of this thesis, I carried out the creation of a new annotated linguistic resource. This resource is annotated with 6 types of propaganda techniques, which breaks down into 14 sub-categories of propaganda in the political debates of the US presidential campaigns from 1960 to 2016. The data set I built contains 1666 instances of propagandist text.; La désinformation, dont la propagation s’est accentuée par le biais des médias sociaux, suscite aujourd’hui une réelle menace pour la société. Il existe différents moyens de véhiculer de la désinformation, par exemple par le biais de contenus délibérément manipulés ou fabriqués dans le but de créer des théories conspirationnistes, de rumeurs ou encore de positions et jugements erronés, tels que l’on peut en rencontrer dans des articles d'actualité, discours et débats politiques. L'une des nombreuses formes de désinformation rencontrée en ligne, et certainement l'une des plus dangereuses, est la propagande. Ce type de désinformation, que l’on retrouve notamment en politique, représente une stratégie de communication efficace mais souvent trompeuse utilisée pour promouvoir un certain point de vue auprès du public. La nécessité d'identifier, de classifier et de comprendre efficacement et automatiquement ce type de phénomène devient pressant. Dans cette thèse, j'aborde cette question et je propose une approche de classification fine des textes polarisés et de propagande issus d’articles de presse et de débats politiques. Selon le sujet abordé, le contexte, la source d'information, les antécédents et les préférences constituent un panel de facteurs pouvant influer sur les perceptions de l’auditoire et donc conduire à sa déviation ou polarisation en faveur d’un parti. À partir d’un cas d’utilisation provenant d’un scénario politique, nous proposons d’explorer les impacts d’une telle polarisation par le biais de méthodes issues de l’analyse de sentiment basée sur des aspects. L’objectif étant de vérifier dans quelle mesure ces méthodes peuvent permettre d’obtenir des informations sur les messages politiques postés sur les médias sociaux. Plus particulièrement, la thèse traite de la conception et de l'évaluation d'un certain nombre de techniques d'extraction des principales caractéristiques des textes de propagande dans le domaine du Traitement Automatique du Langage Naturel (TALN). L'analyse de sentiment, les techniques de persuasion, la simplicité des messages et l'argumentation y sont notamment proposées et étudiées en profondeur. Les résultats de cette thèse montrent que ces caractéristiques peuvent capturer des propriétés particulières permettant de caractériser la propagande dans les textes. D’autre part, ces caractéristiques sont employées dans le cadre de la conception et l'implémentation d'une architecture neuronale ayant pour vocation à détecter et classifier les techniques de propagande à grain fin. Le travail proposé dans cette thèse va au-delà de l'état de l'art des systèmes actuels de détection et de classification de la propagande à grain fin. En effet, plusieurs approches d'apprentissage automatique, allant de la régression logistique à des architectures neuronales récentes, ont été testées sur des jeux de données standard de détection de la propagande. En conséquence, un pipeline complet de détection et de classification de la propagande est présenté. La tâche de détection des extraits de textes de propagande a obtenu un score F1 de 0,71, et l'architecture basée sur les transformateurs a obtenu une moyenne de 0,67 pour la tâche de classification des techniques de propagande, surpassant ainsi les systèmes de pointe. Ce pipeline est démontré avec un outil de preuve de concept appelé PROTECT. Enfin, comme dernière contribution de cette thèse, j'ai participé à la création d'une nouvelle ressource linguistique annotée. Composée de textes issus des débats politiques des campagnes présidentielles américaines de 1960 à 2016, cette ressource est annotée avec 6 types de techniques de propagande qui se décomposent en 14 sous-catégories de propagande. L'ensemble de données que j'ai construit contient 1666 instances de propagande.

    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Vorakitphan, Vorakit;

    La désinformation, dont la propagation s’est accentuée par le biais des médias sociaux, suscite aujourd’hui une réelle menace pour la société. Il existe différents moyens de véhiculer de la désinformation, par exemple par le biais de contenus délibérément manipulés ou fabriqués dans le but de créer des théories conspirationnistes, de rumeurs ou encore de positions et jugements erronés, tels que l’on peut en rencontrer dans des articles d'actualité, discours et débats politiques. L'une des nombreuses formes de désinformation rencontrée en ligne, et certainement l'une des plus dangereuses, est la propagande. Ce type de désinformation, que l’on retrouve notamment en politique, représente une stratégie de communication efficace mais souvent trompeuse utilisée pour promouvoir un certain point de vue auprès du public. La nécessité d'identifier, de classifier et de comprendre efficacement et automatiquement ce type de phénomène devient pressant. Dans cette thèse, j'aborde cette question et je propose une approche de classification fine des textes polarisés et de propagande issus d’articles de presse et de débats politiques. Selon le sujet abordé, le contexte, la source d'information, les antécédents et les préférences constituent un panel de facteurs pouvant influer sur les perceptions de l’auditoire et donc conduire à sa déviation ou polarisation en faveur d’un parti. À partir d’un cas d’utilisation provenant d’un scénario politique, nous proposons d’explorer les impacts d’une telle polarisation par le biais de méthodes issues de l’analyse de sentiment basée sur des aspects. L’objectif étant de vérifier dans quelle mesure ces méthodes peuvent permettre d’obtenir des informations sur les messages politiques postés sur les médias sociaux. Plus particulièrement, la thèse traite de la conception et de l'évaluation d'un certain nombre de techniques d'extraction des principales caractéristiques des textes de propagande dans le domaine du Traitement Automatique du Langage Naturel (TALN). L'analyse de sentiment, les techniques de persuasion, la simplicité des messages et l'argumentation y sont notamment proposées et étudiées en profondeur. Les résultats de cette thèse montrent que ces caractéristiques peuvent capturer des propriétés particulières permettant de caractériser la propagande dans les textes. D’autre part, ces caractéristiques sont employées dans le cadre de la conception et l'implémentation d'une architecture neuronale ayant pour vocation à détecter et classifier les techniques de propagande à grain fin. Le travail proposé dans cette thèse va au-delà de l'état de l'art des systèmes actuels de détection et de classification de la propagande à grain fin. En effet, plusieurs approches d'apprentissage automatique, allant de la régression logistique à des architectures neuronales récentes, ont été testées sur des jeux de données standard de détection de la propagande. En conséquence, un pipeline complet de détection et de classification de la propagande est présenté. La tâche de détection des extraits de textes de propagande a obtenu un score F1 de 0,71, et l'architecture basée sur les transformateurs a obtenu une moyenne de 0,67 pour la tâche de classification des techniques de propagande, surpassant ainsi les systèmes de pointe. Ce pipeline est démontré avec un outil de preuve de concept appelé PROTECT. Enfin, comme dernière contribution de cette thèse, j'ai participé à la création d'une nouvelle ressource linguistique annotée. Composée de textes issus des débats politiques des campagnes présidentielles américaines de 1960 à 2016, cette ressource est annotée avec 6 types de techniques de propagande qui se décomposent en 14 sous-catégories de propagande. L'ensemble de données que j'ai construit contient 1666 instances de propagande. In recent years, disinformation has become more viral, mainly due to its spread online on social media, leading to potential threatening consequences for the society. Heterogeneous forms of online disinformation are possible, i.e., deliberately manipulated or fabricated content with the intentional aim of creating conspiracy theories, rumours, or misbehaved stances and judgements, for instance, in news articles, and political discourse and debates. One of many instances of online disinformation, and certainly one of the most dangerous ones, is propaganda. This disinformation instance represents an effective but often misleading communication strategy which is employed to promote a certain viewpoint to the audience, for instance in the political context. The need to effectively and automatically identify, classify and understand such phenomenon is becoming a urgent need. In this thesis, I tackle this issue and I propose a fine-grained classification approach of polarized and propagandist text in news articles and political debates. More precisely, as the audience' perceptions are perceived differently depending on the context, the source of information, the audience background and preferences, a discussed topic can deviate or polarize the audience into a partisanship. This thesis firstly investigates such polarization given a use-case in a political scenario using Aspects-Based Sentiment Analysis to verify how extensively these methods can be employed to gain insights from the political posts on social media. The thesis discusses the design and evaluation of a number of techniques in extracting the main features of propagandist text in the area of Natural Language Processing (NLP) where sentiment analysis, persuasion techniques, message simplicity, and ultimately argumentation are proposed and thoroughly investigated. The findings in this thesis show that such features can capture particular characteristics of propaganda in texts. Furthermore, these features are employed to tackle the NLP tasks of propaganda detection and classification through the design and implementation of a neural architecture to classify fine-grained propaganda techniques. The work in this thesis goes beyond the state-of-the-art of current systems for fine-grained propaganda detection and classification. Various Machine Learning approaches ranging from feature-based logistic regression to recent neural architectures have been experimented on standard benchmarks in propaganda detection. As a result, a full pipeline in propaganda detection and classification is presented where the task of detecting the propagandist text snippets obtained .71 F1-score, and the transformer-based architecture obtained an average of .67 F1-score for the task of propaganda technique classification, outperforming the state-of-the-art systems. This pipeline is demonstrated with a proof-of-concept tool called PROTECT. Finally, as a last contribution of this thesis, I carried out the creation of a new annotated linguistic resource. This resource is annotated with 6 types of propaganda techniques, which breaks down into 14 sub-categories of propaganda in the political debates of the US presidential campaigns from 1960 to 2016. The data set I built contains 1666 instances of propagandist text.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ INRIA a CCSD electro...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ INRIA a CCSD electro...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Ferrari, Erika;

    Le patrimoine métallique est un témoin culturel de notre passé et, pour cette raison, sa préservation et sa transmission aux générations futures sont importantes. Plusieurs stratégies sont utilisées pour la protection du patrimoine cuivreux exposée en extérieur, dont l’utilisation des inhibiteurs de corrosion organiques. Les inhibiteurs utilisés pour le patrimoine sont généralement empruntés au domaine de l’industrie. Cependant, l’état de surface du métal, couvert par des couches de produits de corrosion complexes, et le protocole d’application des inhibiteurs diffèrent considérablement de l’application industrielle.La présente étude porte spécifiquement sur les inhibiteurs de corrosion pour la conservation des artefacts exposés à base de cuivre par une approche physico-chimique innovante. L'approche prend en compte la complexité de la couche de corrosion étudiée : une plaque de cuivre naturellement corrodée, représentative de la corrosion extérieure à long terme a été choisie. Pour l'étude, trois molécules organiques, caractérisées par des fonctions chimiques différentes ont été sélectionnées comme inhibiteurs de test : le benzotriazole (BTAH), un composé azolé, employé en conservation, dont l'efficacité est débattue et l’utilisation déconseillée en raison de sa toxicité ; l'acide décanoïque (HC10) un acide gras à longue chaîne qui a été proposé comme traitement pour les objets patrimoniaux ; l'acide benzotriazole-5-carboxylique (5CBT), un composé à fonctions mixtes azole-carboxyliques. La réactivité des inhibiteurs avec des phases minérales synthétiques représentatives des produits de corrosion ainsi que des échantillons corrodés anciens (100 ans) avant et après 6 mois d'exposition extérieure ont été étudiées en combinant des observations à l'échelle nanométrique (MET, FIB-tomographie) à celles obtenues à l'échelle microscopique (Raman, MEB-EDS) et des observations globales/globales (couleur, tension de surface, XRD). Des expériences complémentaires en milieux marqués ont permis d'étudier les évolutions de perméabilité (immersion en D₂O) et de comportement passif (immersion KBr). Deux mécanismes réactionnels ont été observés et une relation avec l'efficacité et la durabilité de l'inhibition est proposée. Les molécules caractérisées par la fonction azole (BTAH et 5CBT) réagissent selon un mécanisme d'adsorption-précipitation formant un complexe amorphe adsorbé (film nanométrique) sur la phase minérale substrat (cuprite et brochantite). Les deux traitements sur les couches anciennes de corrosion diffèrent par leur profondeur de pénétration, la formation du complexe BTAH étant détectée jusqu'à la couche interne de cuprite, tandis que la complexation 5CBT n'est observée que dans la partie externe de la brochantite. Ceci a un impact sur la perméabilité de l'eau et la passivité pour les traitements au BTAH qui montrent les meilleurs résultats, et suggère une formation de complexe Cu-BTA sur la partie externe de la couche de cuprite dans ce dernier traitement. La fonction carboxylique dans HC10 conduit à la précipitation du décanoate de cuivre par un mécanisme de dissolution-précipitation. Des cristaux de décanoate se forment sur la surface externe de brochantite : cela confère une quasi-superhydrophobie à l'échantillon après traitement. Cependant, le manque de liaison chimique forte entre le précipité et la surface induit la perte de la couche hydrophobe déposée en surface après 6 mois d'exposition à l'extérieur.En plus de ces résultats phénoménologiques, une nouvelle méthodologie basée sur l'expérience KBr pour tester les inhibiteurs des artefacts corrodés par le cuivre est également proposée. Metallic heritage artefacts represent cultural traces of our past, and for this reason, their preservation and transmission to future generations is important. To protect copper-based artworks exposed outdoors, several conservation strategies are followed, including the use of organic corrosion inhibitors. Inhibitors are usually borrowed from the industrial field. However, the surface state of the metal with the presence of complex corrosion layers, and the protocol of inhibitors' application differ considerably from the industrial ones.The present study specifically addresses corrosion inhibitors for conservation of copper-based exposed artifacts by an innovative physico-chemical approach. The approach takes into account the complexity of the corrosion layer under investigation: a naturally corroded copper plate, representative for outdoor long-term corrosion have been chosen. For the study, three organic molecules, characterized by different chemical functions have been selected as test inhibitors: benzotriazole (BTAH), an azole compound, employed in conservation, which efficiency is debated and its use discouraged due to toxicity; decanoic acid (HC10) a long-chain fatty acid that has been proposed as treatment for heritage objects; benzotriazole-5-carboxylic acid (5CBT), a compound with mixed azole-carboxylic functions.The reactivity of the inhibitors with synthetic mineral phases representative of corrosion products as well as ancient corroded samples (100 years) before and after 6-months outdoor exposure have been investigated by combining observations at the nanoscale (TEM, FIB-tomography) to those obtained at the microscale (Raman, SEM-EDS) and global/bulk observations (colour, surface tension, XRD). Additional experiments in marked environment allowed to investigate changes in permeability (D₂O immersion) and the evolution of passive behavior (KBr immersion).Two reaction mechanisms have been observed and a relationship with the efficiency and durability of the inhibition is proposed. The molecules BTAH and 5CBT interaction with copper atoms occurs via the azole function and both molecules react according to an adsorption-precipitation mechanism forming an adsorbed amorphous complex (nanometric film) on the substrate mineral phase (cuprite and brochantite). The two treatments on the ancient corrosion layers differ for their depth of penetration, with Cu-BTAH complex formation being detected until the cuprite inner layer, while 5CBT complexation is observed only in the outer part of the brochantite. This has an impact on the water permeability and passivity, with the BTAH treatments showing the best results, and suggests a complex formation with the outer cuprite layer in this last treatment. The carboxylic function in HC10 leads to the precipitation of copper decanoate by a dissolution-precipitation mechanism. Crystals of decanoate are formed on the outer surface of brochantite: this confers near super-hydrophobicity to the sample after treatment. However, the lack of bond between the precipitate and the surface determines the loss of the surface-deposited hydrophobic layer after 6 months of outdoor exposure.In addition to these phenomenological results, a new methodology based on the KBr experiment for testing inhibitors for copper corroded artefacts is also proposed.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ HAL-CEAarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    HAL-CEA
    Doctoral thesis . 2021
    Data sources: HAL-CEA
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ HAL-CEAarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      HAL-CEA
      Doctoral thesis . 2021
      Data sources: HAL-CEA
  • Authors: Gainon de Forsan de Gabriac, Clara;

    The last decade has witnessed the impressive expansion of Deep Learning (DL) methods, both in academic research and the private sector. This success can be explained by the ability DL to model ever more complex entities. In particular, Representation Learning methods focus on building latent representations from heterogeneous data that are versatile and re-usable, namely in Natural Language Processing (NLP). In parallel, the ever-growing number of systems relying on user data brings its own lot of challenges. This work proposes methods to leverage the representation power of NLP in order to learn rich and versatile user representations.Firstly, we detail the works and domains associated with this thesis. We study Recommendation. We then go over recent NLP advances and how they can be applied to leverage user-generated texts, before detailing Generative models.Secondly, we present a Recommender System (RS) that is based on the combination of a traditional Matrix Factorization (MF) representation method and a sentiment analysis model. The association of those modules forms a dual model that is trained on user reviews for rating prediction. Experiments show that, on top of improving performances, the model allows us to better understand what the user is really interested in in a given item, as well as to provide explanations to the suggestions made.Finally, we introduce a new task-centered on UR: Professional Profile Learning. We thus propose an NLP-based framework, to learn and evaluate professional profiles on different tasks, including next job generation.; La dernière décennie a vu s’imposer le développement des méthodes de Deep Learning (DL), aussi bien dans le monde académique qu’industriel. Ce succès peut s’expliquer par la capacité du DL à modéliser des entités toujours plus complexes. En particulier, les méthodes de Representation Learning se concentrent sur l’apprentissage de représentations latentes issues de données hétérogènes, à la fois versatiles et réutilisables, notamment en Natural Language Processing (NLP). En parallèle, le nombre grandissant de systèmes reposant sur des données utilisateurs entraînent leur lot de défis.Cette thèse propose des méthodes tirant partie du pouvoir de représentation du NLP pour apprendre des représentations d’utilisateur riches et versatiles. D'abord, nous étudions la Recommandation. Nous parlons ensuite des récentes avancées du NLP et des moyens de les appliquer de façon à tirer partie des textes écrits par les utilisateurs, pour enfin détailler les modèles génératifs. Puis, nous présentons un Système de Recommandation fondé sur la combinaison, d’une méthode de représentation par factorisation matricielle traditionnelle, et d’un modèle d’analyse de sentiments. Nos expériences montrent que, en plus d’améliorer les performances, ce modèle nous permet de comprendre ce qui intéresse l’utilisateur chez un produit, et de fournir des explications concernant les suggestions émises par le modèle. Enfin, nous présentons une nouvelle tâche centrée sur la représentation d’utilisateur : l’apprentissage de profil professionnel. Nous proposons un cadre de travail pour l’apprentissage et l’évaluation des profils professionnels sur différentes tâches, notamment la génération du prochain job.

    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
Advanced search in Research products
Research products
arrow_drop_down
Searching FieldsTerms
Any field
arrow_drop_down
includes
arrow_drop_down
The following results are related to Digital Humanities and Cultural Heritage. Are you interested to view more results? Visit OpenAIRE - Explore.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Buriola, Giulia;
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Archivio della ricer...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Archivio della ricer...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Angelini, EMMA PAOLA MARIA VIRGINIA; Grassini, Sabrina; Peters, MANUEL JACQUES HELENA;
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Publications Open Re...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Publications Open Re...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: van Beek, Martinus Josephus Maria;

    This dissertation explores the function of architecture in the illustrated manuscripts of the erudite Spanish Benedictine scholar, artist and preacher Juan Ricci de Guevara. Among architectural historians, Ricci has become famous for his invention of the complete architectural Salomonic order, which has been discussed by modern scholars predominantly isolated from its textual context, and from a formal, aesthetic approach. The new, comprehensive approach of Ricci’s scholarship in the manuscripts shows that he referred to architecture continuously. From this starting point the hypothesis is made that architecture for Ricci was a suitable interdisciplinary agent for his innovative ideas. With architecture, he could establish connections between various sources, methods and arguments, while coincidentally maintaining the scientific level of his scholarly work. This dissertation is the first book in which Ricci’s written oeuvre (which was never published and is now kept in Madrid, El Escorial, the Vatican and Montecassino) is assessed in-depth comprehensively. It results in a detailed insight in his formulation of a pivotal role for architecture and the architectural image in seventeenth-century scholarship, as a result of Ricci’s particular fusion of scholarly, artistic and rhetorical approaches. The recognition of this mechanism results in an updated inventory of his manuscripts, a discussion of important but hitherto unknown sections of the writings in which the position of architecture is discussed and legitimized, an adjustment of the modern formal discussion of the complete Salomonic order, a new analysis of Ricci’s presentation of his ideas to Pope Alexander VII in the 1660s, and the identification of a decoration program by Ricci for the basilica of the abbey of Montecassino.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ NARCIS; Vrije Univer...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    NARCIS
    Doctoral thesis . 2021
    Data sources: NARCIS
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ NARCIS; Vrije Univer...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      NARCIS
      Doctoral thesis . 2021
      Data sources: NARCIS
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: van Beek, M.J.M.;

    This dissertation explores the function of architecture in the illustrated manuscripts of the erudite Spanish Benedictine scholar, artist and preacher Juan Ricci de Guevara. Among architectural historians, Ricci has become famous for his invention of the complete architectural Salomonic order, which has been discussed by modern scholars predominantly isolated from its textual context, and from a formal, aesthetic approach. The new, comprehensive approach of Ricci’s scholarship in the manuscripts shows that he referred to architecture continuously. From this starting point the hypothesis is made that architecture for Ricci was a suitable interdisciplinary agent for his innovative ideas. With architecture, he could establish connections between various sources, methods and arguments, while coincidentally maintaining the scientific level of his scholarly work. This dissertation is the first book in which Ricci’s written oeuvre (which was never published and is now kept in Madrid, El Escorial, the Vatican and Montecassino) is assessed in-depth comprehensively. It results in a detailed insight in his formulation of a pivotal role for architecture and the architectural image in seventeenth-century scholarship, as a result of Ricci’s particular fusion of scholarly, artistic and rhetorical approaches. The recognition of this mechanism results in an updated inventory of his manuscripts, a discussion of important but hitherto unknown sections of the writings in which the position of architecture is discussed and legitimized, an adjustment of the modern formal discussion of the complete Salomonic order, a new analysis of Ricci’s presentation of his ideas to Pope Alexander VII in the 1660s, and the identification of a decoration program by Ricci for the basilica of the abbey of Montecassino.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Vrije Universiteit A...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Vrije Universiteit A...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
  • image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
    Authors: Herron, Donald;

    This study is an examination of the evolution of teachers’ in-service education and continuous professional development in Ireland between 1945 and 1995. The purpose is to investigate the evolution and development of in-service policy, its goals, construction, participation, implementation and outcomes. The objectives are to deepen educators’ understanding of the current in-service issues by locating them in their broader temporal context and to extend the range of policy options considered by providing a basis for comparison with past situations. Its focus is the professional development policies and implementation strategies adopted by the Department of Education, the development and pursuit of policy positions among teachers, school management organisations and teacher educators, and the transactions between them in the evolution of in-service education and training of primary teachers in the Republic of Ireland. The in-service policy antecedents of the three decades prior to 1950 are explored to identify contemporary policies and practices and examine what foundations and legacies they contributed to primary teachers’ in-service education and training between 1945-1995. There were three separate primary-level level in-service initiatives in the 1950s and 1960s, one by the teachers’ union, the INTO, another by the Catholic Church and a Department of Education revision of Irish language. The breadth and depth of the curriculum reforms required Inspectorates to change approaches to in-service policy and practices. Comprehensive primary curriculum reform commenced in 1967 and its dissemination was planned by the Department around policy decisions on and coordinated implementation of strategically interrelated features including in-service training. An In-service Steering Committee, established in 1970, attempted to coordinate various institutions’ in-service contributions. The Committee advocated teacher centres, which when established from 1972, created an atmosphere of local optimism. In the absence of adequate resources or Steering Committee agreement on an encompassing in-service plan, an insufficiency of activities ensued which was curtailed by the mid-1970s recession. Dissatisfaction with the consequences of budget cuts resulted in a review of in-service education policies in 1980. The report of the Committee on In-service Education was ignored and its main recommendation, a national in-service agency, was deferred. There was an increase in the quantity of short course but this did not address access, course depth or continuity or address emerging in-service priorities or deficiencies. The decade from 1987 witnessed a period analysis, national policy making and deliberative processes involved in achieving an education policy consensus. In the case of in-service education and in-career development, departmental preferences with regard to structure, prioritisation of curriculum implementation and defining which in-service activities were funded, preceded the policy-making processes. The preferred option was solidified by the conditionality of the funding source, the European Structural Fund. The policy process, stimulated by the 1991 OECD contributions, expanded a departmental conceptualisation of curriculum-focused in-service training to school-focused organisational, staff and teacher professional development.

    image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Research Repository ...arrow_drop_down
    image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
    Research Repository UCD
    Doctoral thesis . 2021
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Research Repository ...arrow_drop_down
      image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
      Research Repository UCD
      Doctoral thesis . 2021
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Gundersen, Ingar Mørkestøl;

    A growing body of climate data points towards a significant climate cooling in the northern hemisphere during the 6th century AD. Linked to multiple explosive volcanic eruptions between AD 536-547, the cooling event is the coldest that has been documented for the last 2000 years and seems to have persisted, to varying degrees, well into the latter half of the 6th century. Several researchers have claimed that the 6th-century cooling must have resulted in extensive crop failure throughout Scandinavia, followed by famine, plagues, and social unrest. One hypothesis suggests that the population of the Scandinavian Peninsula may have been halved as a result. The combination of prolonged cooling and presumed crop failure is often compared to Norse myths about the Fimbulwinter, but critics argue that the Fimbulwinter hypothesis is rife with the uncritical use of climate data, a lack of source criticism and deterministic conclusions. In many ways, the ongoing discourse follows in line with previous discourses in archaeology, revolving around an artificial dichotomy between crisis and continuity. In this thesis, I examine the climatic and archaeological premises for the Fimbulwinter hypothesis and discuss it against developing theoretical frameworks within the environmental humanities. By using vulnerability and resilience as analytical tools, the subsistence and settlement patterns of selected landscapes are analysed against the possibility of crop failure and famine, with emphasis on the Gudbrandsdalen valley and the Lake Mjøsa region in the inlands of eastern Norway. I conclude that climate cooling had the potential to critically impact some areas, while others were seemingly less affected. These results suggest significant regional diversity in the consequences and adaptations in relation to the 6th-century cooling event. The hypothesis of a halving of the population is up for revision, but the crisis narrative still cannot be fully discounted. This thesis is also available in the Zenodo archive: https://doi.org/10.5281/zenodo.5782896

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    ZENODO
    Other literature type . 2021
    License: CC BY
    Data sources: ZENODO
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    ZENODO
    Thesis . 2021
    License: CC BY
    Data sources: Datacite
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    addClaim

    This Research product is the result of merged Research products in OpenAIRE.

    You have already added works in your ORCID record related to the merged Research product.
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    visibility121
    visibilityviews121
    downloaddownloads113
    Powered by Usage counts
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      ZENODO
      Other literature type . 2021
      License: CC BY
      Data sources: ZENODO
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      ZENODO
      Thesis . 2021
      License: CC BY
      Data sources: Datacite
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      addClaim

      This Research product is the result of merged Research products in OpenAIRE.

      You have already added works in your ORCID record related to the merged Research product.
  • Authors: Vorakitphan, Vorakit;

    In recent years, disinformation has become more viral, mainly due to its spread online on social media, leading to potential threatening consequences for the society. Heterogeneous forms of online disinformation are possible, i.e., deliberately manipulated or fabricated content with the intentional aim of creating conspiracy theories, rumours, or misbehaved stances and judgements, for instance, in news articles, and political discourse and debates. One of many instances of online disinformation, and certainly one of the most dangerous ones, is propaganda. This disinformation instance represents an effective but often misleading communication strategy which is employed to promote a certain viewpoint to the audience, for instance in the political context. The need to effectively and automatically identify, classify and understand such phenomenon is becoming a urgent need. In this thesis, I tackle this issue and I propose a fine-grained classification approach of polarized and propagandist text in news articles and political debates. More precisely, as the audience' perceptions are perceived differently depending on the context, the source of information, the audience background and preferences, a discussed topic can deviate or polarize the audience into a partisanship. This thesis firstly investigates such polarization given a use-case in a political scenario using Aspects-Based Sentiment Analysis to verify how extensively these methods can be employed to gain insights from the political posts on social media. The thesis discusses the design and evaluation of a number of techniques in extracting the main features of propagandist text in the area of Natural Language Processing (NLP) where sentiment analysis, persuasion techniques, message simplicity, and ultimately argumentation are proposed and thoroughly investigated. The findings in this thesis show that such features can capture particular characteristics of propaganda in texts. Furthermore, these features are employed to tackle the NLP tasks of propaganda detection and classification through the design and implementation of a neural architecture to classify fine-grained propaganda techniques. The work in this thesis goes beyond the state-of-the-art of current systems for fine-grained propaganda detection and classification. Various Machine Learning approaches ranging from feature-based logistic regression to recent neural architectures have been experimented on standard benchmarks in propaganda detection. As a result, a full pipeline in propaganda detection and classification is presented where the task of detecting the propagandist text snippets obtained .71 F1-score, and the transformer-based architecture obtained an average of .67 F1-score for the task of propaganda technique classification, outperforming the state-of-the-art systems. This pipeline is demonstrated with a proof-of-concept tool called PROTECT. Finally, as a last contribution of this thesis, I carried out the creation of a new annotated linguistic resource. This resource is annotated with 6 types of propaganda techniques, which breaks down into 14 sub-categories of propaganda in the political debates of the US presidential campaigns from 1960 to 2016. The data set I built contains 1666 instances of propagandist text.; La désinformation, dont la propagation s’est accentuée par le biais des médias sociaux, suscite aujourd’hui une réelle menace pour la société. Il existe différents moyens de véhiculer de la désinformation, par exemple par le biais de contenus délibérément manipulés ou fabriqués dans le but de créer des théories conspirationnistes, de rumeurs ou encore de positions et jugements erronés, tels que l’on peut en rencontrer dans des articles d'actualité, discours et débats politiques. L'une des nombreuses formes de désinformation rencontrée en ligne, et certainement l'une des plus dangereuses, est la propagande. Ce type de désinformation, que l’on retrouve notamment en politique, représente une stratégie de communication efficace mais souvent trompeuse utilisée pour promouvoir un certain point de vue auprès du public. La nécessité d'identifier, de classifier et de comprendre efficacement et automatiquement ce type de phénomène devient pressant. Dans cette thèse, j'aborde cette question et je propose une approche de classification fine des textes polarisés et de propagande issus d’articles de presse et de débats politiques. Selon le sujet abordé, le contexte, la source d'information, les antécédents et les préférences constituent un panel de facteurs pouvant influer sur les perceptions de l’auditoire et donc conduire à sa déviation ou polarisation en faveur d’un parti. À partir d’un cas d’utilisation provenant d’un scénario politique, nous proposons d’explorer les impacts d’une telle polarisation par le biais de méthodes issues de l’analyse de sentiment basée sur des aspects. L’objectif étant de vérifier dans quelle mesure ces méthodes peuvent permettre d’obtenir des informations sur les messages politiques postés sur les médias sociaux. Plus particulièrement, la thèse traite de la conception et de l'évaluation d'un certain nombre de techniques d'extraction des principales caractéristiques des textes de propagande dans le domaine du Traitement Automatique du Langage Naturel (TALN). L'analyse de sentiment, les techniques de persuasion, la simplicité des messages et l'argumentation y sont notamment proposées et étudiées en profondeur. Les résultats de cette thèse montrent que ces caractéristiques peuvent capturer des propriétés particulières permettant de caractériser la propagande dans les textes. D’autre part, ces caractéristiques sont employées dans le cadre de la conception et l'implémentation d'une architecture neuronale ayant pour vocation à détecter et classifier les techniques de propagande à grain fin. Le travail proposé dans cette thèse va au-delà de l'état de l'art des systèmes actuels de détection et de classification de la propagande à grain fin. En effet, plusieurs approches d'apprentissage automatique, allant de la régression logistique à des architectures neuronales récentes, ont été testées sur des jeux de données standard de détection de la propagande. En conséquence, un pipeline complet de détection et de classification de la propagande est présenté. La tâche de détection des extraits de textes de propagande a obtenu un score F1 de 0,71, et l'architecture basée sur les transformateurs a obtenu une moyenne de 0,67 pour la tâche de classification des techniques de propagande, surpassant ainsi les systèmes de pointe. Ce pipeline est démontré avec un outil de preuve de concept appelé PROTECT. Enfin, comme dernière contribution de cette thèse, j'ai participé à la création d'une nouvelle ressource linguistique annotée. Composée de textes issus des débats politiques des campagnes présidentielles américaines de 1960 à 2016, cette ressource est annotée avec 6 types de techniques de propagande qui se décomposent en 14 sous-catégories de propagande. L'ensemble de données que j'ai construit contient 1666 instances de propagande.

    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Vorakitphan, Vorakit;

    La désinformation, dont la propagation s’est accentuée par le biais des médias sociaux, suscite aujourd’hui une réelle menace pour la société. Il existe différents moyens de véhiculer de la désinformation, par exemple par le biais de contenus délibérément manipulés ou fabriqués dans le but de créer des théories conspirationnistes, de rumeurs ou encore de positions et jugements erronés, tels que l’on peut en rencontrer dans des articles d'actualité, discours et débats politiques. L'une des nombreuses formes de désinformation rencontrée en ligne, et certainement l'une des plus dangereuses, est la propagande. Ce type de désinformation, que l’on retrouve notamment en politique, représente une stratégie de communication efficace mais souvent trompeuse utilisée pour promouvoir un certain point de vue auprès du public. La nécessité d'identifier, de classifier et de comprendre efficacement et automatiquement ce type de phénomène devient pressant. Dans cette thèse, j'aborde cette question et je propose une approche de classification fine des textes polarisés et de propagande issus d’articles de presse et de débats politiques. Selon le sujet abordé, le contexte, la source d'information, les antécédents et les préférences constituent un panel de facteurs pouvant influer sur les perceptions de l’auditoire et donc conduire à sa déviation ou polarisation en faveur d’un parti. À partir d’un cas d’utilisation provenant d’un scénario politique, nous proposons d’explorer les impacts d’une telle polarisation par le biais de méthodes issues de l’analyse de sentiment basée sur des aspects. L’objectif étant de vérifier dans quelle mesure ces méthodes peuvent permettre d’obtenir des informations sur les messages politiques postés sur les médias sociaux. Plus particulièrement, la thèse traite de la conception et de l'évaluation d'un certain nombre de techniques d'extraction des principales caractéristiques des textes de propagande dans le domaine du Traitement Automatique du Langage Naturel (TALN). L'analyse de sentiment, les techniques de persuasion, la simplicité des messages et l'argumentation y sont notamment proposées et étudiées en profondeur. Les résultats de cette thèse montrent que ces caractéristiques peuvent capturer des propriétés particulières permettant de caractériser la propagande dans les textes. D’autre part, ces caractéristiques sont employées dans le cadre de la conception et l'implémentation d'une architecture neuronale ayant pour vocation à détecter et classifier les techniques de propagande à grain fin. Le travail proposé dans cette thèse va au-delà de l'état de l'art des systèmes actuels de détection et de classification de la propagande à grain fin. En effet, plusieurs approches d'apprentissage automatique, allant de la régression logistique à des architectures neuronales récentes, ont été testées sur des jeux de données standard de détection de la propagande. En conséquence, un pipeline complet de détection et de classification de la propagande est présenté. La tâche de détection des extraits de textes de propagande a obtenu un score F1 de 0,71, et l'architecture basée sur les transformateurs a obtenu une moyenne de 0,67 pour la tâche de classification des techniques de propagande, surpassant ainsi les systèmes de pointe. Ce pipeline est démontré avec un outil de preuve de concept appelé PROTECT. Enfin, comme dernière contribution de cette thèse, j'ai participé à la création d'une nouvelle ressource linguistique annotée. Composée de textes issus des débats politiques des campagnes présidentielles américaines de 1960 à 2016, cette ressource est annotée avec 6 types de techniques de propagande qui se décomposent en 14 sous-catégories de propagande. L'ensemble de données que j'ai construit contient 1666 instances de propagande. In recent years, disinformation has become more viral, mainly due to its spread online on social media, leading to potential threatening consequences for the society. Heterogeneous forms of online disinformation are possible, i.e., deliberately manipulated or fabricated content with the intentional aim of creating conspiracy theories, rumours, or misbehaved stances and judgements, for instance, in news articles, and political discourse and debates. One of many instances of online disinformation, and certainly one of the most dangerous ones, is propaganda. This disinformation instance represents an effective but often misleading communication strategy which is employed to promote a certain viewpoint to the audience, for instance in the political context. The need to effectively and automatically identify, classify and understand such phenomenon is becoming a urgent need. In this thesis, I tackle this issue and I propose a fine-grained classification approach of polarized and propagandist text in news articles and political debates. More precisely, as the audience' perceptions are perceived differently depending on the context, the source of information, the audience background and preferences, a discussed topic can deviate or polarize the audience into a partisanship. This thesis firstly investigates such polarization given a use-case in a political scenario using Aspects-Based Sentiment Analysis to verify how extensively these methods can be employed to gain insights from the political posts on social media. The thesis discusses the design and evaluation of a number of techniques in extracting the main features of propagandist text in the area of Natural Language Processing (NLP) where sentiment analysis, persuasion techniques, message simplicity, and ultimately argumentation are proposed and thoroughly investigated. The findings in this thesis show that such features can capture particular characteristics of propaganda in texts. Furthermore, these features are employed to tackle the NLP tasks of propaganda detection and classification through the design and implementation of a neural architecture to classify fine-grained propaganda techniques. The work in this thesis goes beyond the state-of-the-art of current systems for fine-grained propaganda detection and classification. Various Machine Learning approaches ranging from feature-based logistic regression to recent neural architectures have been experimented on standard benchmarks in propaganda detection. As a result, a full pipeline in propaganda detection and classification is presented where the task of detecting the propagandist text snippets obtained .71 F1-score, and the transformer-based architecture obtained an average of .67 F1-score for the task of propaganda technique classification, outperforming the state-of-the-art systems. This pipeline is demonstrated with a proof-of-concept tool called PROTECT. Finally, as a last contribution of this thesis, I carried out the creation of a new annotated linguistic resource. This resource is annotated with 6 types of propaganda techniques, which breaks down into 14 sub-categories of propaganda in the political debates of the US presidential campaigns from 1960 to 2016. The data set I built contains 1666 instances of propagandist text.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ INRIA a CCSD electro...arrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ INRIA a CCSD electro...arrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
  • image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    Authors: Ferrari, Erika;

    Le patrimoine métallique est un témoin culturel de notre passé et, pour cette raison, sa préservation et sa transmission aux générations futures sont importantes. Plusieurs stratégies sont utilisées pour la protection du patrimoine cuivreux exposée en extérieur, dont l’utilisation des inhibiteurs de corrosion organiques. Les inhibiteurs utilisés pour le patrimoine sont généralement empruntés au domaine de l’industrie. Cependant, l’état de surface du métal, couvert par des couches de produits de corrosion complexes, et le protocole d’application des inhibiteurs diffèrent considérablement de l’application industrielle.La présente étude porte spécifiquement sur les inhibiteurs de corrosion pour la conservation des artefacts exposés à base de cuivre par une approche physico-chimique innovante. L'approche prend en compte la complexité de la couche de corrosion étudiée : une plaque de cuivre naturellement corrodée, représentative de la corrosion extérieure à long terme a été choisie. Pour l'étude, trois molécules organiques, caractérisées par des fonctions chimiques différentes ont été sélectionnées comme inhibiteurs de test : le benzotriazole (BTAH), un composé azolé, employé en conservation, dont l'efficacité est débattue et l’utilisation déconseillée en raison de sa toxicité ; l'acide décanoïque (HC10) un acide gras à longue chaîne qui a été proposé comme traitement pour les objets patrimoniaux ; l'acide benzotriazole-5-carboxylique (5CBT), un composé à fonctions mixtes azole-carboxyliques. La réactivité des inhibiteurs avec des phases minérales synthétiques représentatives des produits de corrosion ainsi que des échantillons corrodés anciens (100 ans) avant et après 6 mois d'exposition extérieure ont été étudiées en combinant des observations à l'échelle nanométrique (MET, FIB-tomographie) à celles obtenues à l'échelle microscopique (Raman, MEB-EDS) et des observations globales/globales (couleur, tension de surface, XRD). Des expériences complémentaires en milieux marqués ont permis d'étudier les évolutions de perméabilité (immersion en D₂O) et de comportement passif (immersion KBr). Deux mécanismes réactionnels ont été observés et une relation avec l'efficacité et la durabilité de l'inhibition est proposée. Les molécules caractérisées par la fonction azole (BTAH et 5CBT) réagissent selon un mécanisme d'adsorption-précipitation formant un complexe amorphe adsorbé (film nanométrique) sur la phase minérale substrat (cuprite et brochantite). Les deux traitements sur les couches anciennes de corrosion diffèrent par leur profondeur de pénétration, la formation du complexe BTAH étant détectée jusqu'à la couche interne de cuprite, tandis que la complexation 5CBT n'est observée que dans la partie externe de la brochantite. Ceci a un impact sur la perméabilité de l'eau et la passivité pour les traitements au BTAH qui montrent les meilleurs résultats, et suggère une formation de complexe Cu-BTA sur la partie externe de la couche de cuprite dans ce dernier traitement. La fonction carboxylique dans HC10 conduit à la précipitation du décanoate de cuivre par un mécanisme de dissolution-précipitation. Des cristaux de décanoate se forment sur la surface externe de brochantite : cela confère une quasi-superhydrophobie à l'échantillon après traitement. Cependant, le manque de liaison chimique forte entre le précipité et la surface induit la perte de la couche hydrophobe déposée en surface après 6 mois d'exposition à l'extérieur.En plus de ces résultats phénoménologiques, une nouvelle méthodologie basée sur l'expérience KBr pour tester les inhibiteurs des artefacts corrodés par le cuivre est également proposée. Metallic heritage artefacts represent cultural traces of our past, and for this reason, their preservation and transmission to future generations is important. To protect copper-based artworks exposed outdoors, several conservation strategies are followed, including the use of organic corrosion inhibitors. Inhibitors are usually borrowed from the industrial field. However, the surface state of the metal with the presence of complex corrosion layers, and the protocol of inhibitors' application differ considerably from the industrial ones.The present study specifically addresses corrosion inhibitors for conservation of copper-based exposed artifacts by an innovative physico-chemical approach. The approach takes into account the complexity of the corrosion layer under investigation: a naturally corroded copper plate, representative for outdoor long-term corrosion have been chosen. For the study, three organic molecules, characterized by different chemical functions have been selected as test inhibitors: benzotriazole (BTAH), an azole compound, employed in conservation, which efficiency is debated and its use discouraged due to toxicity; decanoic acid (HC10) a long-chain fatty acid that has been proposed as treatment for heritage objects; benzotriazole-5-carboxylic acid (5CBT), a compound with mixed azole-carboxylic functions.The reactivity of the inhibitors with synthetic mineral phases representative of corrosion products as well as ancient corroded samples (100 years) before and after 6-months outdoor exposure have been investigated by combining observations at the nanoscale (TEM, FIB-tomography) to those obtained at the microscale (Raman, SEM-EDS) and global/bulk observations (colour, surface tension, XRD). Additional experiments in marked environment allowed to investigate changes in permeability (D₂O immersion) and the evolution of passive behavior (KBr immersion).Two reaction mechanisms have been observed and a relationship with the efficiency and durability of the inhibition is proposed. The molecules BTAH and 5CBT interaction with copper atoms occurs via the azole function and both molecules react according to an adsorption-precipitation mechanism forming an adsorbed amorphous complex (nanometric film) on the substrate mineral phase (cuprite and brochantite). The two treatments on the ancient corrosion layers differ for their depth of penetration, with Cu-BTAH complex formation being detected until the cuprite inner layer, while 5CBT complexation is observed only in the outer part of the brochantite. This has an impact on the water permeability and passivity, with the BTAH treatments showing the best results, and suggests a complex formation with the outer cuprite layer in this last treatment. The carboxylic function in HC10 leads to the precipitation of copper decanoate by a dissolution-precipitation mechanism. Crystals of decanoate are formed on the outer surface of brochantite: this confers near super-hydrophobicity to the sample after treatment. However, the lack of bond between the precipitate and the surface determines the loss of the surface-deposited hydrophobic layer after 6 months of outdoor exposure.In addition to these phenomenological results, a new methodology based on the KBr experiment for testing inhibitors for copper corroded artefacts is also proposed.

    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ HAL-CEAarrow_drop_down
    image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
    HAL-CEA
    Doctoral thesis . 2021
    Data sources: HAL-CEA
    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ HAL-CEAarrow_drop_down
      image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
      HAL-CEA
      Doctoral thesis . 2021
      Data sources: HAL-CEA
  • Authors: Gainon de Forsan de Gabriac, Clara;

    The last decade has witnessed the impressive expansion of Deep Learning (DL) methods, both in academic research and the private sector. This success can be explained by the ability DL to model ever more complex entities. In particular, Representation Learning methods focus on building latent representations from heterogeneous data that are versatile and re-usable, namely in Natural Language Processing (NLP). In parallel, the ever-growing number of systems relying on user data brings its own lot of challenges. This work proposes methods to leverage the representation power of NLP in order to learn rich and versatile user representations.Firstly, we detail the works and domains associated with this thesis. We study Recommendation. We then go over recent NLP advances and how they can be applied to leverage user-generated texts, before detailing Generative models.Secondly, we present a Recommender System (RS) that is based on the combination of a traditional Matrix Factorization (MF) representation method and a sentiment analysis model. The association of those modules forms a dual model that is trained on user reviews for rating prediction. Experiments show that, on top of improving performances, the model allows us to better understand what the user is really interested in in a given item, as well as to provide explanations to the suggestions made.Finally, we introduce a new task-centered on UR: Professional Profile Learning. We thus propose an NLP-based framework, to learn and evaluate professional profiles on different tasks, including next job generation.; La dernière décennie a vu s’imposer le développement des méthodes de Deep Learning (DL), aussi bien dans le monde académique qu’industriel. Ce succès peut s’expliquer par la capacité du DL à modéliser des entités toujours plus complexes. En particulier, les méthodes de Representation Learning se concentrent sur l’apprentissage de représentations latentes issues de données hétérogènes, à la fois versatiles et réutilisables, notamment en Natural Language Processing (NLP). En parallèle, le nombre grandissant de systèmes reposant sur des données utilisateurs entraînent leur lot de défis.Cette thèse propose des méthodes tirant partie du pouvoir de représentation du NLP pour apprendre des représentations d’utilisateur riches et versatiles. D'abord, nous étudions la Recommandation. Nous parlons ensuite des récentes avancées du NLP et des moyens de les appliquer de façon à tirer partie des textes écrits par les utilisateurs, pour enfin détailler les modèles génératifs. Puis, nous présentons un Système de Recommandation fondé sur la combinaison, d’une méthode de représentation par factorisation matricielle traditionnelle, et d’un modèle d’analyse de sentiments. Nos expériences montrent que, en plus d’améliorer les performances, ce modèle nous permet de comprendre ce qui intéresse l’utilisateur chez un produit, et de fournir des explications concernant les suggestions émises par le modèle. Enfin, nous présentons une nouvelle tâche centrée sur la représentation d’utilisateur : l’apprentissage de profil professionnel. Nous proposons un cadre de travail pour l’apprentissage et l’évaluation des profils professionnels sur différentes tâches, notamment la génération du prochain job.

    0
    citations0
    popularityAverage
    influenceAverage
    impulseAverage
    BIP!Powered by BIP!
    more_vert