Hi, I'm Julia! I'm a PhD candidate at the University of Michigan School of Information, advised by Ceren Budak and supported by a Google PhD Fellowship. I completed my BA in Linguistics (2018) and MS in Computer Science (2019) at Stanford University, where I was advised by Dan Jurafsky.

My research interests include natural language processing, political communication, and computational sociolinguistics. In particular, I am interested in developing computational methods to better understand (1) the framing of complex sociopolitical issues in social media, and the broader implications of these linguistic choices, (2) how people talk about other people, especially in the representations of marginalized communities, and (3) language variation and change in online communities of practice. Here is my academic CV and Google Scholar profile.

Papers

From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language Models
Julia Mendelsohn, Ronan Le Bras, Yejin Choi, and Maarten Sap
Association for Computational Linguistics (ACL), 2023
Link.

Bridging Nations: Quantifying the Role of Multilinguals in Communication on Social Media
Julia Mendelsohn, Sayan Ghosh, David Jurgens, and Ceren Budak
International Conference on Web and Social Media (ICWSM), 2023
Link.

Challenges and Opportunities in Information Manipulation Detection: An Examination of Wartime Russian Media
Chan Young Park*, Julia Mendelsohn*, Anjalie Field*, and Yulia Tsvetkov
Findings of the 2022 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP), 2022
Link. [* = equal contribution]

Computational analysis of 140 years of US political speeches reveals more positive but increasingly polarized framing of immigration
Dallas Card, Serina Chang, Chris Becker, Julia Mendelsohn, Rob Voigt, Leah Boustan, Ran Abramitzky, and Dan Jurafsky
Proceedings of the National Academy of Sciences 119(31), 2022
Link.

Detecting Community Sensitive Norm Violations in Online Conversations
Chan Young Park, Julia Mendelsohn, Karthik Radhakrishnan, Kinjal Jain, Tushar Kanakagiri, David Jurgens and Yulia Tsvetkov
Proceedings of the Findings of the 2021 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP), 2021
Link.

Modeling Framing in Immigration Discourse on Social Media
Julia Mendelsohn, Ceren Budak, and David Jurgens
Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021
Link. Github.

A framework for the computational linguistic analysis of dehumanization
Julia Mendelsohn, Yulia Tsvetkov, and Dan Jurafsky
Frontiers in Artificial Intelligence, 2020
Link. PDF.

Using sentiment induction to understand variation in gendered online communities
Li Lucy and Julia Mendelsohn
Society for Computation in Linguistics (SCiL), 2019
Link. Poster.

Iris: A conversational agent for complex tasks
Ethan Fast, Binbin Chen, Julia Mendelsohn, Jonathan Bassen, and Michael S Bernstein
CHI Conference on Human Factors in Computing Systems, 2018
Link. Github.

Presentations

Sounding the Bullhorn: Surfacing and Analyzing Dogwhistles with Language Models
Julia Mendelsohn, Maarten Sap, and Ronan Le Bras
New Ways of Analyzing Variation (NWAV) 50, October 2022.
Text as Data (TADA), October 2022.

Challenges in Opinion Manipulation Detection: An Examination of Wartime Russian Media
Julia Mendelsohn, Sayan Ghosh, Ceren Budak & David Jurgens
Chan Young Park, Julia Mendelsohn, Anjalie Field, and Yulia Tsvetkov
Text as Data (TADA), October 2022.

Bridging nations: Quantifying the influence of multilinguals in the European Twitter network
Julia Mendelsohn, Sayan Ghosh, Ceren Budak & David Jurgens
International Conference on Computational Social Science (IC2S2), July 2021
Slides.

Modeling the framing of immigration on social media
Julia Mendelsohn, Ceren Budak & David Jurgens
North American Chapter of the Association for Computational Linguistics (NAACL), May 2021
International Conference on Computational Social Science (IC2S2), July 2021
Politics and Computational Social Science Conference (PaCSS), August 2021
Slides. Poster.

A framework for the computational linguistic analysis of dehumanization
Julia Mendelsohn, Yulia Tsvetkov & Dan Jurafsky
International Conference on Computational Social Science (IC2S2), July 2020
Slides.

The social meaning of diphthong fronting in Berlin German
Stefanie Jannedy, Melanie Weirich, Gediminas Schüppenhauer & Julia Mendelsohn
Phonetik und Phonologie Tagung in Düsseldorf, Germany, September 2019

Computational linguistic analysis of dehumanization of LGBTQ groups in the media
Julia Mendelsohn
New Ways of Analyzing Variation (NWAV) 47, October 2018
Poster.

Cross-community variation in onset /l/ among California Latinx speakers
Podesva, R., F. Conover, A. Flores-Perez, C. Gratton, A. Kane, D. Leigh, Julia Mendelsohn, C. Rentie & A. Sprenger
New Ways of Analyzing Variation (NWAV) 46, November 2017
Slides.