Abstract: Traditionally, misinformation has been identified by contrasting a claim with established relevant facts. Whether this identification is done by algorithmic means or human acumen, the establishment of relevant facts requires encyclopedic knowledge about a larger world beyond a single document. This raises epistemological concerns: such as "what is included in this encyclopedic knowledge?" and "what do we accept as trustworthy information?" In this talk, I focus on medical information that travels across distinct genres where the language and the audience are drastically different, and demonstrate how to discover relevant facts as well as how trust is sometimes manipulated (intentionally or otherwise) to deceive the recipient. Finally, I conclude the talk with a dissection of the current challenges in identifying misinformation and deception in natural language, signaling avenues for future research.
Bio: Dr. Ritwik Banerjee is a Research Assistant Professor of Computer Science at Stony Brook University. His interests include knowledge discovery, natural language inference, and misinformation analysis. These have made him venture into applications in precision healthcare, such as the prediction of adverse drug events in emergency rooms, and into information extraction from financial corpora. His most recent work has been on empirical investigations into cross-genre misinformation, specifically in health news. He has delved into not just fake news in itself, but also the use of deceptive linguistic and extra-linguistic cues in their presentation. His research has received support from the National Science Foundation (NSF) as well as from the industry. Dr. Banerjee has served on a number of program committees for international conferences and workshops. He received his Ph.D. in Computer Science from Stony Brook University, preceded by an M.Sc. in Computer Science, and B.Sc. in Mathematics, both from the Chennai Mathematical Institute (India).