COVID-19

Social and Physical Sensing Enabled Decision Support

Project Overview
Motto	To measure psychological impact of COVID-19 on the population and identify its main factors.

Psychidemic: Measuring the Spatio-Temporal Psychological Impact of Novel Coronavirus with a Social Quality Index

Abstract:

Experts have warned about severe social and health consequences of COVID-19 on individuals and society, specifically Mental Health (Depression, Anxiety), Addiction (Substance-use), and Gender-based (or Domestic) Violence (GBV). Building upon past successful efforts involving social media big data analysis for epidemiology and public health research, such as drug abuse (leading to an FDA warning), mental health, harassment, and GBV, we undertook the analysis of over 800 million tweets and over 700,000 news articles related to COVID-19 to explore a variety of questions such as: Q1: How can we use social media to measure psychological and social impact in (near) real-time? Q2: How does intervention in the form of state-level policy choices and implementations relate to mental health and addiction-related behaviors across different states? What evidence is there for adaptive/coping behavior? Q3: How do GenZ and Millennials express themselves in the outbreak, particularly in the context of mental health and addiction? This research involves the use of the knowledge-infused natural language processing developed at the AI Institute. It involves infusing (deeply integrating) deep domain knowledge (e.g., mental health-related knowledge from DSM-5 and addition related knowledge captured by the Drug Abuse Ontology) with the deep learning techniques. Please find an extended abstract here: [1] and a detailed ongoing report here: [2]

Articles in Media

• The Conversation: We’re measuring online conversation to track the social and mental health issues surfacing during the coronavirus pandemic *Healthline:What Your Social Media Posts Say About Your Stress Level Right Now

Relevant Articles/Publication on Research Used in the above work:

1. Gaur, M., Kursuncu, U., Sheth, A. Yadav, S. & Wickramarachchi (2020), "Hypertext 2020 Tutorial: Knowledge-infused Deep Learning", In 31st ACM Conference on Hypertext and Social Media (HT'20), Florida, USA
2. Ugur Kursuncu, Manas Gaur,Usha Lokala,Krishnaprasad Thirunarayan,Amit Sheth and I. Budak Arpinar. "Predictive Analysis on Twitter: Techniques and Applications". Book Chapter in "Emerging Research Challenges and Opportunities in Computational Social Network Analysis and Mining", Editor: Nitin Agarwal, Springer, 2018.

Tutorials

• Gaur, M., Kursuncu, U., Sheth, A. Yadav, S. & Wickramarachchi (2020), "Hypertext 2020 Tutorial: Knowledge-infused Deep Learning", In 31st ACM Conference on Hypertext and Social Media (HT'20), Florida, USA

   Shades of Knowledge-Infused Learning for Enhancing Deep Learning
   Importance of background knowledge in Context Modeling
   Sentinels of Breach: Lexical Choice as a Measure of Urgency in Social Media
   Mapping social media to clinically grounded mental health categories in DSM-5 for a comprehensive understanding of mental illness
   Assessment of severity of mental illness from social media
   Identifying Personal Communication and Sentiment in Drug-Related Tweets

Related Projects

Concurrent Projects

• Context-Aware Harassment Detection on Social Media
• Project Safe Neighborhood
• EdrugTrends
• Innovative NIDA National Early Warning Sysetm Network (iN3)
  
• MIDAS
• Market Driven Innovations and Scaling up of Twitris
• Modeling Social Behavior for Healthcare Utilization in Depression
• kHealth: Semantic Multisensory Mobile Approach to Personalized Asthma Care