Samuel Carton

Postdoctoral Fellow

Computer Science
University of Colorado Boulder
Office: DLC 170, 1095 Regent Drive, Boulder, CO 48104
Email: samuel DOT carton AT colorado DOT edu

I am a postdoctoral fellow in computer science at University of Colorado Boulder, where I work with Chenhao Tan. I did my PhD at the University of Michigan School of Information with Qiaozhu Mei and Paul Resnick . I received my Bachelor's degree from Northwestern University, where I was advised by Doug Downey and Brent Hecht.


I'm interested in interpretable machine learning. I like working on new algorithms for opening up black box models, as well as trying to figure out how to deploy them in ways that help people make better decisions. More generally, I'm a huge fan of the fair, accountable and transparent machine learning (FATML) movement, and I'm exited about algorithms and applications thereof.

I've been working for a while on dealing with toxic language online. I think this is an important domain area that affects the subjective experience of millions of individual people, but also larger-scale phenomena like political discourse. It's also one where NLP/ML have a big potential to improve the status quo because so much of it is about how things are said rather than what's being said (which is harder for automated methods to deal with).

I've done previous work in misinformation, predictive policing and scientometrics. I'd be excited to return to any of these topics, particularly from the perspective of FAT methods.

Research Group

I am currently a member of Chenhao Tan's research group. As a PhD student I'was a a member of Qiaozhu Mei's research group, The Foreseers, as well as the University of Michigan Center for Social Media Responsibility


  • Samuel Carton, Qiaozhu Mei, and Paul Resnick. 2020. Feature-Based Explanations Don't Help People Detect Misclassifications of Online Toxicity. In Proceedings of the International AAAI Conference on Web and Social Media. [pdf]
  • Vivian Lai, Samuel Carton, and Chenhao Tan. 2020. Harnessing Explanations to Bridge AI and Humans. In CHI 2020 Fair & Responsible AI Workshop. [pdf]
  • Cristina Garbacea, Samuel Carton, Shiyan Yan, and Qiaozhu Mei. 2019. Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval [pdf][code]
  • Samuel Carton, Qiaozhu Mei, and Paul Resnick. 2018. Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. [pdf][code]
  • Jennifer Helsby, Samuel Carton, Kenneth Joseph, Ayesha Mahmud, Youngsoo Park, Andrea Navarrete, Klaus Ackermann, Joe Walsh, Lauren Haynes, Crystal Cody, Major Estella Patterson, and Rayid Ghani. 2018. Early Intervention Systems: Predicting Adverse Interactions Between Police and the Public. Criminal Justice Policy Review [pdf]
  • Samuel Carton, Rayid Ghani, Jennifer Helsby, Kenneth Joseph, Ayesha Mahmud, Youngsoo Park, Joe Walsh, Crystal Cody, CPT Estella Patterson, and Lauren Haynes. 2016. Identifying Police Officers at Risk of Adverse Events. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining [pdf][more info]
  • Samuel Carton, Souneil Park, Nicole Zeffer, Eytan Adar, Qiaozhu Mei, and Paul Resnick. 2015. Audience Analysis for Competing Memes in Social Media. In Ninth International AAAI Conference on Web and Social Media. [pdf]
  • Paul Resnick, Samuel Carton, Souneil Park, Yuncheng Shen, and Nicole Zeffer. 2014. RumorLens: A System for Analyzing the Impact of Rumors and Corrections in Social Media. In Proceedings of the Computation + Journalism Symposium. [pdf]
  • Brent Hecht, Samuel H. Carton, Mahmood Quaderi, Johannes Schöning, Martin Raubal, Darren Gergle, and Doug Downey. 2012. Explanatory semantic relatedness and explicit spatialization for exploratory search. In Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval. [pdf] [more info]
  • Patti Bao, Brent Hecht, Samuel Carton, Mahmood Quaderi, Michael Horn, and Darren Gergle. 2012. Omnipedia: bridging the wikipedia language gap. In Proceedings of the 2012 ACM annual conference on Human Factors in Computing Systems. [pdf]