Information retrieval and extraction on COVID-19 clinical articles using graph community detection and Bio-BERT embeddings

In this paper, we present an information retrieval system on a corpus of scientific articles related to COVID-19. We build a similarity network on the articles where similarity is determined via shared citations and biological domain-specific sentence embeddings. Ego-splitting community detection on the article network is employed to cluster the articles and then the queries are matched with the clusters. Extractive summarization using BERT and PageRank methods is used to provide responses to the query. We also provide a Question-Answer bot on a small set of intents to demonstrate the efficacy of our model for an information extraction module. © ACL 2020.All right reserved.

Opportunities from Disruption - How lifelong learning helped create more connected classrooms

The coronavirus pandemic has led to instructors worldwide seeking ways to engage students better through virtual platforms. As the world interacts online, more than ever before, this paper reflects on an educator’s experience with the virtual teaching and learning spaces pre and during the ongoing pandemic © 2022 American Society for Engineering Education.

A Semester Like No Other: Use of Natural Language Processing for Novice-Led Analysis on End-of-Semester Responses on Students' Experience of Changing Learning Environments Due to COVID-19

In response to campus closures due to COVID-19, the learning environment in a foundational engineering course unexpectedly shifted from hands-on, collaborative work to remote delivery, accomplished within a short period of time. Through end-of-semester course surveys, students were asked open-ended questions to get feedback about their experience with the goal of using student feedback for curriculum planning and improvement should there be continued need to facilitate the course remotely in subsequent semesters. However, with 1,170 responses, the volume of data made it challenging to analyze, interpret and use the feedback for decision-making for following semesters. To address this challenge, we utilized Natural Language Processing (NLP) based techniques - algorithmic ways to analyze, interpret, and present words and sentiments from student responses visually, to inform a novice-led analysis to ultimately help with course planning for future semesters. © American Society for Engineering Education, 2021

A Grounded Theory Analysis of COVID-19 Information and Resources Relayed Through University Webpages: Implications for a More Inclusive Community

This qualitative study investigates web pages documenting COVID-19 responses from 28 universities across the United States. Using grounded theory methodology, we inductively developed a model of universities' response to the pandemic. Four types of strategies were identified from the data and a theoretical model was developed describing (a) causal conditions that underlie the strategies for response to the pandemic, (b) the context that influenced the strategies adopted by the universities, (c) intervening conditions due to the pandemic that influenced strategy development, and (d) potential recommendations to make universities' responses more inclusive. This research has implications for improving the experience of the communities a university serves, including faculty development, especially for newer faculty who are joining the universities remotely and interacting with new colleagues only through the virtual mediums. Finally, this paper will be of use to engineering educators and administrators as they seek to improve inclusion and belonging within faculty at universities. © American Society for Engineering Education, 2021

Self-isolation of healthcare workers during covid-19 pandemic in a tertiary care center – association between their sleep quality, anxiety status and social capital

With the rapid spread of COVID-19 since its inception a year back, the frontline healthcare workers, who underwent isolation and quarantine following possible exposure, faced multiple psychiatric problems like deterioration of sleep quality and anxiety manifestations. Different demographic variables were found to be associated with their occurrence, as well as inter-relation between them were found to be common. We tried to examine the role of social support system as well to the appearance of such problems in the present study. After getting the ethical clearance, willing healthcare workers during their isolation and quarantine were presented questionnaires consisting of Socio-demographic proforma, Self-rating Anxiety Scale (SAS), Personal Social Capital Scale 16 (PSCS) and Pittsburgh Sleep Quality Index (PSQI). Data taken were analysed with independent t test and Fishers exact chi square test, Pearson’s correlation analysis and linear regression analysis. Majority of the subjects were married Hindu female from urban background, mostly doctor and nurse by profession. Independent T test revealed significant association between gender and anxiety status as well as between marital status and sleep quality. Positive correlation between the PSCS scores and the SAS scores (r=0.652, P<0.01) and negative correlations between the PSCS and PSQI scores and between the SAS and PSQI score were found albeit being statistically insignificant. Significant association was found between the SAS score and social bridging component of PSCS (Fishers exact chi sq. value 0.54 and p = 0.003). Anxiety score was significantly affected when the socio-demographic factors like gender, religion, marital status and scores of sleep quality (PSQI) and social capital (PSCS) were considered together as seen in the linear regression analysis.