Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection

A drastic rise in potentially life-threatening misinformation has been a by-product of the COVID-19 pandemic. Computational support to identify false information within the massive body of data on the topic is crucial to prevent harm. Researchers proposed many methods for flagging online misinformation related to COVID-19. However, these methods predominantly target specific content types (e.g., news) or platforms (e.g., Twitter). The methods’ capabilities to generalize were largely unclear so far. We evaluate fifteen Transformer-based models on five COVID-19 misinformation datasets that include social media posts, news articles, and scientific papers to fill this gap. We show tokenizers and models tailored to COVID-19 data do not provide a significant advantage over general-purpose ones. Our study provides a realistic assessment of models for detecting COVID-19 misinformation. We expect that evaluating a broad spectrum of datasets and models will benefit future research in developing misinformation detection systems. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A Multitask Learning Approach for Fake News Detection: Novelty, Emotion, and Sentiment Lend a Helping Hand

The recent explosion in false information on social media has led to intensive research on automatic fake news detection models and fact-checkers. Fake news and misinformation, due to its peculiarity and rapid dissemination, have posed many interesting challenges to the Natural Language Processing (NLP) and Machine Learning (ML) community. Admissible literature shows that novel information includes the element of surprise, which is the principal characteristic for the amplification and virality of misinformation. Novel and emotional information attracts immediate attention in the reader. Emotion is the presentation of a certain feeling or sentiment. Sentiment helps an individual to convey his emotion through expression and hence the two are co-related. Thus, Novelty of the news item and thereafter detecting the Emotional state and Sentiment of the reader appear to be three key ingredients, tightly coupled with misinformation. In this paper we propose a deep multitask learning model that jointly performs novelty detection, emotion recognition, sentiment prediction, and misinformation detection. Our proposed model achieves the state-of-the-art(SOTA) performance for fake news detection on three benchmark datasets, viz. ByteDance, Fake News Challenge(FNC), and Covid-Stance with 11.55%, 1.58%, and 21.76% improvement in accuracy, respectively. The proposed approach also shows the efficacy over the single-task framework with an accuracy gain of 11.53, 28.62, and 14.31 percentage points for the above three datasets. The source code is available at https://github.com/Nish-19/MultitaskFake-News-NES.

Assessment of online learning procedure through the eyes of medical students in COVID-19 scenario

Introduction: Coronavirus Disease 2019 (COVID-19) pandemic has necessitated closure of physical classroom for maintaining social distancing norms, prompting learning environment to shift from offline to online. Medical education has also undergone similar changes, and online education and assessment methods had to be implemented. Student's perception regarding the same was assessed through this study. Aim: To assess the perception of first year MBBS students about the online education and assessment during the lockdown period of two months. Materials and Methods: A descriptive cross-sectional study was carried out on the first year MBBS students of North Bengal Medical College (NBMCH) during the COVID-19 Lockdown period. All first year MBBS students of NBMCH were added in WhatsApp groups created for academic purposes by Department of Anatomy, NBMCH during the lockdown period. Respective teachers in the academic groups carried out sharing of Digital Education Material (DEM), holding Online Interaction (OI) and correspondence with students, and taking Online Assessments (OA) through sharing questions framed in Google Forms. After two months, the perception of the students was assessed through a voluntary participation based online survey designed in google forms, the results of which were tabulated later and analysed. Results: A total 95 students (54 Male, 41 Female) out of 200 had participated in the survey. Most students were reliant on smartphones (n=90, 94.7%) and mobile internet (n=78, 82%). Most agreed on DEM being relevant (83.2%) and informative (80.7%) but showed diverging opinion on ease of understanding, revision and overall fulfillment of learning objective. On OI majority students responded positively on promptness, relevancy, informative and helpfulness but only 46.8% considered DEM and OI fulfilled the overall learning objective. Regarding OA students had an overall positive opinion. Comparing the online mode with offline, students mostly preferred the latter, though agreeing that online method of education was effective and it was easier to score in OAs. Conclusion: While most students accepted online education, interaction and assessment positively, at the end most of them still preferred offline mode of education and assessment. This could reflect lack of student-student interaction and indicated need of further studies to explore the matter, to help us approach online education better.