• Digital Humanities and Cultural Heritage
• Other research productsclose
• Education and Research Archive close

Presented at the Linked Archives 2022: International Workshop on Archives and Linked Data at the 26th International Conference on Theory and Practice of Digital Libraries (TPDL2022), Padua, Italy.

Archaeology in 2021 was characterized by a continued call to use the tools of the discipline to document the violence of settler colonialism in the past and present, pushing anthropology to reckon with its own role in perpetuating historical trauma. The tension between disciplinary reflection and reform was most clearly articulated in the use of archaeological geophysics to detect the unmarked graves of incarcerated Indigenous children who died at residential and boarding schools in Canada and the United States. The highly publicized investigation of these schools has brought renewed attention to issues of repatriation and historical reclamation for many communities impacted by settler colonialism. These discussions have reverberated throughout the discipline, prompting revisions to the Society for American Archaeology's “Statement Concerning the Treatment of Human Remains,” reopening conversations around an African American Graves Protection and Repatriation Act, and informing debates around the ethics of DNA research. These conversations are part of a larger movement toward decolonizing the field by using archaeological methods to explore marginalized histories and support communities most impacted by the violences of settler colonialism.

Call Centers or Support Centers in different companies aggregate huge amount of audio data everyday. From all the conversations, few conversations demonstrate the disappointment of clients towards services, products or delivery. Finding the sentiment of the customer helps in determining whether the customer was satisfied with the service, product or not. However, manually analyzing the huge amount of audio data is time consuming, laborious, and burdensome. The aim of this research is to develop the deep learning based model which would enable to automatically evaluate the sentiment of a customer throughout a conversation with a call center agent. In this work, we developed Long Term Short Memory (LSTM) based deep learning models for customer audio call data analysis. The proposed pipeline consists of two sequential steps: a) Audio transcription: speech recognition of the conversations and document them in text; and b) Sentiment Analysis: conduct the sentiment analysis on the text data using Natural Language Processing (NLP). We compute spectrogram features from audio data and then fine-tune the LSTM based Deep Speech Model using customer call data. Deep Speech model can successfully transcribe the conversations between client and call center agent in a text form. Then we compute the 1-gram feature from text data which find the occurrence of the words responsible to identify the customer sentiments. We fed this feature into a LSTM based deep architecture which would enable to detect customer sentiments from text data. Recent advances in natural language understanding and generation facilitates to detect customer sentiments successfully as accurate as human experts. Both speech transcription and sentiment analysis part of the proposed tool are very generic in nature which could utilize for other audio data transcription and text sentiment analysis purposes. Tools were developed in python which can be easily transported and adapted in other programming environments.

Software testing is a quality control activity which focuses on detecting defects which are then eventually removed. After completion of coding software products are subjected to system testing with the help of different test cases. These tests are essential and necessary to assess the effectiveness of the software. However, it is impossible to completely test any nontrivial module or system. Theoretically it suffers from halting problem: it is impossible to write a program that tests whether every program halts in a finite amount of time. Practically, executing all test cases involves enormous time and cost. Hence, it is crucial to test a subset of test cases which are important from user’s perspective based on the frequency of usage, criticality, and probability of failure. This research work is limited to test case selection for regression testing which retests software that has been changed or extended by new features during software development. In this research we carried out the following activities to develop a machine learning based test case selection strategy. First, we clean the data by dropping irrelevant features.Then we preprocess the data by encoding categorical features into its numerical values. After that we compute the bag of words for text data such as test case title, which identify the important functionality for test case selection. All these features are fed into machine learning based classifiers, such as Logistic regression, naãve Bayes, Gradient boosting, kNN, Decision tree, and Gaussian process. Experimental results demonstrate that decision tree classifier outperforms other classifiers for software test case selection. This research demonstrates that machine learning-based approach can reduce the bias and manual labour of domain expert for software regression testing. In the future, we would investigate the feature selection strategy for natural language processing to optimize the whole software test case selection procedure

SSHRC IG awarded 2021. With this project, I pursue the legacy of influential documentary photographer Lewis Hine, who developed his techniques in the service of his social science teacher role. I examine the historical moments of exchange, influence, or overlap between the worlds of artists and teachers in North America that occurred as part of the early 20th-century Visual Instruction Movement, when art was used to teach, and when teaching tools resembled art. Alongside Hine's efforts to teach social sciences with the camera in 1900s New York -- an instance of teaching tools becoming art -- I will consider Anna Verona Dorris's efforts to bring historical paintings and National Geographic photographs into geography and history classrooms in 1920s California -- a case where art was used to teach. This research will show how visual materials shape ways of seeing and understanding the world. The work will enrich scholarly understanding of the artistic and pedagogical conventions of particular moments in history, address teachers and the general public with an online exhibition of historical teaching materials and an article published in the Alberta Teachers' Association's ATA Magazine. These public-facing outputs will serve 21st-century communities of teachers and learners by calling attention to the role of visual materials in classrooms, and by exploring the potential of artful visuals to produce meaningful and multi-layered learning experiences.

Although Cree people are one of the native groups of the Plains, and those of us living in Edmonton occupy Treaty 6 territory, there is very little discussion of contemporary cultural practices within our education system. In popular literature, native peoples are often referred to in a past tense, as if their culture too is a thing of the past. For these reasons, I decided to explore how funerary practices have changed for this group after the introduction of colonization to better understand how these people have adapted and continue to adapt to a colonial landscape. In order to do so I will examine ethnographic records and an archaeological burial in an attempt to piece together historical practices. It is important to remember however, that ethnographic records are usually written by colonizers and that archaeological burials cannot accurately represent the ritual aspects of funerary practices. Next, I will current ethnographic accounts of Cree funerals and feasting ceremonies to see how traditions have changed over time.

This essay explores how John S. McClintock’s Pioneer Days in the Black Hills: Accurate History and Facts Related by One of the Early Day Pioneers, originally published in 1939 and republished by the University of Oklahoma Press in 2000, is employed as a historical source by historians and in popular cultural contexts (including by scriptwriters for the HBO series “Deadwood”). The essay underscores palpable tensions in a text in which McClintock presents himself as an eyewitness to key moments in Black Hills history, yet claims not to want to speak of himself. Tracing these tensions in the text reveals interesting insights into how we read and classify forms of life narratives and how those life narratives may serve historical understanding and writing. In writing of a life narrative written by an ancestor, I discuss my own relation to the man and the memoir as well the challenges that arise in working on life narratives by kin.

DYSCORPIA: Future Intersections of the Body and Technology was a two-year interdisciplinary research project that brought together scholars from art and design, music, digital and medical humanities, radiology, computer science and contemporary dance in order to question what it means not to know the limits of our bodies in the face of new technologies. Over two years scholars cross-pollinated their research through seminars and public presentations. The project culminated in a large exhibition of artworks that were exhibited at Enterprise Square Galleries, Edmonton in 2019. The exhibition included over 50 works by international, national, local artists as well as students from the University of Alberta, that were organised under four themes: Stories in Flesh and Bytes, Virtual Consciousness and Artificial Bodies, Out on Our Limbs and Evolving Anatomies. This full color catalogue of the exhibition which includes 12 commissioned essays, full colour images of all the works in the exhibition, as well as a augmented reality gallery, the app for which can be found here https://www.dyscorpia.com/catalogue.

Image processing and analysis has been used in the sciences since before the advent of the personal computer, beginning as early as the 1920s (Gonzalez & Woods, 2002, p. 3-4). The need to improve image quality spurred the beginnings of scientific image processing, in which images are prepared through digital manipulation “for the measurement and analysis of the features and structures that they reveal” (Russ & Neil, 2016, p. xiii). While scientific fields such as medical research, space programs and astronomy were among the first to make use of this software, (Gonzalez & Wood, 2002, p. 5-6), and due to this modern software is geared towards scientific research, it is seeing growing use in other areas such as the arts and humanities. In this study, digitized cover images of fragile mass market paperbacks are used in an exploration of the software Fiji, a build of the image processing and analysis tool, ImageJ. How can Fiji be used in the analysis of non-traditional, non scientific images? What strengths does Fiji have? What weaknesses in analysing these images?

This was an article I wrote in 2007 and published in the Dalhousie Journal of Information Management (now the Dalhousie Journal of Interdisciplinary Management). I wanted to preserve a copy here.