Computational Social Science Seminar: Anjalie Field, Johns Hopkins University
Analyzing Speech as Data in Police Archives
Abstract
While text-as-data studies have become increasingly achievable with the development of user-friendly tools for processing text, speech archives remain an under-utilized resource for computational social science. In this talk, I will discuss our ongoing work to construct speech processing pipelines for analyzing police body camera footage and radio communications. These datasets have the potential to offer valuable insights into policing activity and police-community relations, ultimately improving accountability and effectiveness. However, the large volume of data makes automated processing necessary, and off-the-shelf speech tools perform poorly in this domain. Our work focuses on both developing methodology to adapt models to noisy domain-specific speech and to support accurate high-level conclusions, even when relying on imperfect models. We further aim to increase data availability to other researchers.
About the CSS seminar series
The University of Michigan School of Information’s 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.
Please RSVP for attendance.
Featured Speaker
Anjalie Field
Johns Hopkins University
Anjalie Field is an Assistant Professor in the Computer Science Department at Johns Hopkins University. She is also affiliated with the Center for Language and Speech Processing (CLSP) and the Data Science and AI Institute. Her research focuses on the ethics and social science aspects of natural language processing, which includes developing models to address societal issues like discrimination and propaganda, as well as critically assessing and improving ethics in AI pipelines. Her work has been published in NLP and interdisciplinary venues, like ACL and PNAS, and in 2024 she was named an AI2050 Early Career Fellow by Schmidt Futures. Prior to joining JHU, she was a postdoctoral researcher at Stanford, and she completed her PhD at the Language Technologies Institute at Carnegie Mellon University.
Contact: [email protected]