• Digital Humanities and Cultural Heritage
• Closed Access close
• Publications close
• BA close

Abstract The notion of shameless normalization is applied in the paper to argue that the Serbian ruling party’s press releases introduce shameless normalization of expressing sycophancy toward the leader. Within the framework of critical (political) discourse analysis postulating that social actors’ use of language is vested with interests that need to be linguistically managed, the paper focuses on how the proposed strategies in political discourse – coercion, legitimisation and (mis)representation – manage the interest of the authors of press releases in realization of sycophancy. The analysis shows that the shameless normalization of sycophancy is realized by coercing the recipients to accept the exclusive right of the leader to represent the homogenized people of Serbia (the ingroup). This exclusive right is legitimized through positive representation of the leader as the self of the ingroup. Such legitimisation is enabled by misrepresentation both in terms of quality and quantity of the information conveyed.

Abstract Various approaches to text simplification have been proposed in an attempt to increase text readability. The rephrasing of syntactically and semantically complex structures is still challenging. A pedagogically motivated simplified version of the same text can have both positive and negative side effects. On the one hand, it can facilitate reading comprehension because of much shorter sentences and a limited vocabulary, but on the other hand, the simplified text often lacks coherence, unity and style. Therefore, reasonable trade-offs among linguistic simplicity, naturalness and informativeness are highly needed. This is a survey paper that discusses state-of-the-art approaches to sentence/text simplification and evaluation methods, along with an empirical evaluation of our approach. The quality of sentence splitting, using the knowledge extraction tool SAAT was compared to state-of-the-art syntactic simplification systems. The research was carried out on the WikiSplit, the HSplit and MinWikiSplit simplification corpora. Automatic metrics for the HSplit showed that the SAAT outperformed other TS systems in all categories. For the WikiSplit dataset, automatic metrics scores were slightly lower than that of the baseline system DisSim. However, the human evaluation showed that DisSim outperformed the SAAT in terms of simplicity and grammar. The quality of AG18copy output corresponded to that of the SAAT. The inter-annotator agreement was calculated. Research limitations as well as suggestions for future research were also provided.

With the constant increase in the amount of available information, especially textual, there exists a need for an efficient and automated text summarization mechanism. Two main text summarization algorithms have been the focus of numerous research studies: extractive and abstractive summarization. This paper focuses on implementing a variant of abstractive summarization using Long Short-Term Memory (LSTM) networks by modeling the summarization task as a Sequence-to-Sequence (Seq2Seq) problem. The dataset used in the research was Amazon’s database of food and product reviews. The study employs the encoder-decoder architecture, with stacked LSTMs in the encoder phase and an attention layer mechanism. Moreover, the paper experiments with using bidirectional LSTMs instead of the standard unidirectional approach. This, combined with stacking, leads to increased sequence representation and better summarization performance. The trained model was evaluated using BLEU and ROUGE performance metrics, showing acceptable results. Moreover, the produced summaries generally seemed to correspond to original summaries, conveying the intended meaning. In the end, the paper outlines several possible improvements to be attempted in future models.

In this article state of the art semantic role labeling (SRL) tools have been compared on published lexical resources and custom hand annotated previously unseen texts. Semantic role labeling is one of the first steps into understanding the meaning of the sentence. The process of identifying semantic roles includes several steps from which the main are predicate identification, argument identification and argument classification. All the approaches compared in this article suggest supervised machine learning algorithms on lexical resources. The comparison of the tools for semantic role labeling are tested against hand annotated corpora independent of FrameNet or PropBank corpus. The precision, recall tests were made on PropBank data as well. Because the results of classification can be biased, the objective of this research was to comprise all the mentioned tools with hand annotated previously unseen data. The results have shown that mate-tools has achieved best results on independent hand annotated data with the best micro average F-score of 78% on custom hand annotated dataset. Results from this article were used to evaluate which tool can be used for knowledge extraction tasks and question generation in communication module of intelligent tutoring system. The overview of all freely available tools, mostly from classifier implementation point of view is given in this article.

The world and everyday life are completely changed due to novel Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) which caused COVID-19 disease. New decisions and rules are set from day to day. Reactions and attitudes of people are often shared on social media, especially using Twitter which makes Twitter a good source of data for many researches. In this work, we analyse a dataset of tweets that have at least 1000 retweets to perform sentiment analysis. Python libraries were used for analysis which includes language detection and translation, preprocessing, tokenization and stemming. Moreover, sentiment analysis and classification is performed using Naive Bayes. It is found that most of the tweets have positive sentiment and achieved accuracy is 60%. Classifier is able to predict positive and neutral tweets with high rate, while it has lower accuracy rate for negative sentiment.

Integrated urban planning is based on the necessity of constantly adapting to complex social processes and applying methodology that supports multidisciplinarity, flexibility, and adaptability. In trying to achieve future visions and to meet trends of urbanization, inherited contextual values are often forgotten. Although the impression that everything was better before is based on nostalgia, the urban development history should still be analyzed. This article analyzes principles of integrated urban planning by reviewing twentieth-century development of Banja Luka. The objective is to recognize, to evaluate, and to adapt those principles to the contemporary context and to reconsider them in the future. The analysis shows the positive and negative values of the development, which reveals that the principles of integrated urban planning were present in each period. As their singularity and fragmentation without the systematic integration was not efficient enough, recommendations for improving integrated urban planning in the specific context are given.

The study presents a historical and sociological interpretation of the events that marked the gradual integration of the Bata Company into the Indian economy and society from the mid-1920s to the early 1960s. Within this context, in addition to the general economic, political and cultural developments, particular attention has been devoted to the everyday life of Indian and Czech workers in the Bata company town of Batanagar. The study is based on a comparative-historical analysis of available archival sources and a secondary analysis of the relevant academic literature. The results of the research indicate that during this period, Bata was forced to adapt continuously to the cultural specifics of Indian society, that is, the process of its integration into the Indian economy and society had pronounced glocal characteristics.

In this article we present an knowledge extraction approach that can be used in systems that implement teaching in a fully automated manner. These systems are called Intelligent Tutoring Systems (ITS) and are conceived around the idea of one-to-one teaching. Many such systems use natural language processing to improve the communication interface between student and the system. These techniques can be also used on the content creator side to semi- automate or fully automate the task of teaching content creation. In such systems the knowledge representation plays a crucial role to successfully implement teaching and encourage learning. The output of the knowledge extraction phase is a knowledge in the form of a hyper graph that can be used for adaption to the students current knowledge level. We present a deep neural network architecture for precise POS tagging of words written in languages that are morphologically rich. Using sparse representations for words in this task increases the vector space and makes learning more complex. This problem can be solved to some extent by using traditional vector representations but there is also the problem with representing words that are ambiguous. Proposed architecture uses a Bidirectional Encoder Representations from Transformers (BERT) model that is pre-trained on Croatian language to achieve state-of-the-art accuracy for POS tagging.

This paper explores the work done so far on creating and using digital data regarding stecci – UNESCO-listed world heritage from medieval Bosnia. Firstly, the paper reveals a slow, but steady progress towards creating a wholistic digital catalogue of all existing stecci necropolises and tombstones. Secondly, it discovers an encouraging trend of innovative research methods for analysing these digital data, as well as for production of digital art inspired by these important monuments. Finally, the paper identifies the main problem that hinders faster progress towards ‘digital stecci’ in the costly and somewhat piecemeal approach evidenced in individual endeavours of scholars, professionals and/or artists. More coordinated effort and teamwork is recommended as a way forward.