I’m a PhD student in the Language Technologies Institute at Carnegie Mellon University. I use computational text analysis to study social factors such as identity, power, and influence. My dissertation investigates how people use language to represent their own identities and those of others in social media and online narrative. This work combines methods from natural language processing and machine learning with theories from sociolinguistics, discourse analysis, and the social sciences.

Publications and Presentations

Modeling Unstructured Data: Teachers as Learners and Designers of Technology-enhanced Artificial Intelligence Curriculum
Cansu Tatar, Michael Miller Yoder, Madeleline Coven, Kenia Wiedemann, Jie Chao, William Finzer, Shiyan Jiang, Carolyn Rosé
International Society of the Learning Sciences (ISLS). 2021.
conference presentation

Phans, Stans and Cishets: Self-Presentation Effects on Content Propagation in Tumblr
Michael Miller Yoder, Qinlan Shen, Yansen Wang, Alex Coda, Yunseok Jang, Yale Song, Kapil Thadani, Carolyn P. Rosé
Proceedings of the ACM Conference on Web Science (WebSci). 2020.
conference paper pdf · slides

“Everyone is Gay and Nothing Hurts”: The Presentation of Queer Relationships in Fanfiction
Michael Miller Yoder, Luke Breitfeller, Carolyn P. Rosé
Association for Computers and the Humanities (ACH), Pittsburgh, PA, 2019.
conference presentation slides

Ron the Death Eater: Plotting Characterization from Canon to Fanfiction
Michael Miller Yoder, Qinlan Shen, James Fiacco, Carolyn P. Rosé
Society for Text & Discourse (ST&D), New York, NY, 2019.
conference presentation slides

Perceptions of Censorship and Moderation Bias in Political Debate Forums
Qinlan Shen, Michael Miller Yoder, Yohan Jo, Carolyn P. Rosé
Proceedings of the International AAAI Conference on Web and Social Media (ICWSM). 2018.
conference paper pdf

Unpacking a Political Icon: “Bike Lanes” and Orders of Indexicality
Michael Miller Yoder, Barbara Johnstone
Discourse & Communication. 2018.
journal article article page · preprint · slides

Roles and Success in Wikipedia Talk Pages: Identifying Latent Patterns of Behavior
Keith Maki, Michael Miller Yoder, Yohan Jo, Carolyn P. Rosé
Proceedings of the International Joint Conference on Natural Language Processing (IJCNLP). 2017.
Best Student Paper.
conference paper pdf · data · slides

Modeling Dialogue Acts with Content Word Filtering and Speaker Preferences
Yohan Jo, Michael Miller Yoder, Hyeju Jang, Carolyn P. Rosé
Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). 2017.
conference paper pdf · code

Code-Switching as a Social Act: The Case of Arabic Wikipedia Talk Pages
Michael Miller Yoder, Shruti Rijhwani, Carolyn Penstein Rosé, Lori Levin
Proceedings of the Second Workshop on Natural Language Processing and Computational Social Science (at ACL). 2017.
workshop paper pdf · data · slides

Metaphor Detection with Topic Transition, Emotion and Cognition in Context
Hyeju Jang, Yohan Jo, Qinlan Shen, Michael Miller, Shane Moon, Carolyn P. Rosé
Proceedings of the Association for Computational Linguistics (ACL). 2016.
conference paper pdf