CLASP
The Centre for Linguistic Theory and Studies in Probability

NLP Talk Title: Detecting Implicitly Harmful Language in Political Discourse

Abstract

When discussing politics, people often use subtle linguistic strategies to influence how their audience thinks about issues, which can then impact public opinion and policy. For example, anti-immigration activists may frame immigration as a threat to native born citizens’ jobs, describe immigrants with dehumanizing vermin-related metaphors, or even use coded expressions to covertly connect immigration with antisemitic conspiracy theories. In this talk, I will briefly overview my research program at the intersection of NLP, political framing, and implicitly harmful language. I will primarily focus on work developing foundations for the computational study of dogwhistle communication: messaging that has different meanings for in-group and out-group audiences. Grounded in an ongoing survey of computational research on antisemitism, I will also discuss the urgent need for group-specific resources, explainable models, and socially-grounded evaluation to understand implicit harm both in language analyzed with LLMs and in the models themselves.

Bio: Julia Mendelsohn is an assistant professor at the University of Maryland College of Information and Institute for Advanced Computer Studies. She is also affiliated with the AI Interdisciplinary Institute at Maryland. Her research interests include natural language processing, political communication, and computational sociolinguistics. She is especially interested in developing computational models for understanding subtle and covert rhetoric in online political discussions and the impact of such language, particularly on marginalized communities. Julia has published papers at top-tier natural language processing and computational social science venues, including ACL, NAACL, EMNLP, and ICWSM. Prior to joining UMD, Julia was a postdoc at the University of Chicago Data Science Institute. Julia completed her PhD at the University of Michigan School of Information and received a BA in Linguistics and MS in Computer Science from Stanford University.