Data Science/Computational Social Science Seminar: Kristina Lerman
Psychology of Social Media: Emotions, Conflict, and Mental Health in the Digital Age
Abstract
Social media has linked people on a global scale, rapidly transforming how we communicate and share ideas and feelings. This massive interconnectedness created vulnerabilities in the form of societal division, growing mistrust and deteriorating mental health. My group has developed computational tools to detect emotions in online discussions, providing new insights into the collective psychology of social media. My talk focuses on three case studies: affective polarization, intergroup conflict and psychological contagion. Affective polarization refers to the emotional divide in political polarization, where different groups not only disagree but also dislike and distrust each other. I show that “in-group love, out-group hate” that characterize affective polarization also exist in online interactions. I introduce a model of belief change in affectively polarized systems and show that it explains how out-group hate amplifies groupthink, and why exposure to out-group beliefs, long thought to be the solution to reducing polarization, often backfires. Next, I analyze the language of “othering” and show how fear speech and hate speech work in tandem to fuel intergroup conflict and propaganda campaigns. Turning to mental health, I show that online pro-anorexia communities grow through mechanisms similar to online radicalization. Using generative AI we explore the collective mindsets of online communities to identify unhealthy cognitions that would be missed by traditional moderation. This research provides new insights into the complex social and emotional dynamics of political discourse and mental health in the digital age.
Speaker bio
Kristina Lerman is a senior principal scientist at the University of Southern California Information Sciences Institute and holds a joint appointment as a research professor in the USC Thomas Lord Department of Computer Science. Trained as a physicist, she now applies network analysis and machine learning to problems in computational social science, including crowdsourcing, social network and social media analysis. Her work on modeling and understanding cognitive biases in social networks has been covered by the Washington Post, Wall Street Journal and The Atlantic. She is a fellow of the AAAI.
About the DS/CSS seminar series
The University of Michigan School of Information’s Data Science/Computational Social Science seminar series brings together a vibrant and diverse community of scholars whose cutting-edge research in information science, computer science and the social sciences aims to broaden our understanding of important social and technological issues.
Organizers for the winter 2025 series are UMSI assistant professors Paramveer Dhillon and Sabina Tomkins.