The Computational Social Science faculty host a regular weekly seminar that features invited talks, research presentations, and informal work-in-progress discussions.
Due to in-person gathering restrictions, all seminar talks will be held online via Zoom. Please see the weekly annoucement for a link or contact the Fall 2020 organizer David Jurgens for a link.
Abstract: Intimacy is a fundamental aspect of how we relate to others in social settings. Language encodes the social information of intimacy through both topics and other more subtle cues (such as linguistic hedging and swearing). Here, we introduce a new computational framework for studying expressions of the intimacy in language with an accompanying dataset and deep learning model for accurately predicting the intimacy level of questions. Through analyzing a dataset of 80.5M questions across social media, books, and films, we show that individuals employ interpersonal pragmatic moves in their language to align their intimacy with social settings. Then, in three studies, we further demonstrate how individuals modulate their intimacy to match social norms around gender, social distance, and audience, each validating key findings from studies in social psychology. Our work demonstrates that intimacy is a pervasive and impactful social dimension of language.
Abstract: Birth stories have become increasingly common on the internet, and these unsolicited, publicly posted stories provide rich descriptions of decisions, emotions, and relationships during a common but sometimes traumatic medical experience. The personal details included in these stories can be illuminating for medical practitioners, and due to their shared structures, birth stories are also an ideal testing ground for computational narrative analysis techniques. In this talk, I'll present an analysis of 2,847 birth stories from an online forum and discuss our discovery of clear sentiment, topic, and persona-based patterns. These patterns both model the expected narrative event sequences of birth stories and highlight diverging pathways and exceptions to narrative norms in this community.
© 2019 Regents of the University of Michigan
