 |
Director: Professor Matthew Lease ACM Distinguished Member • AAAI Senior Member Publications • Datasets & Software • Slides 1616 Guadalupe Ste 5.202 |
Overview: Our research spans artificial Intelligence (AI) modeling and human-computer interaction (HCI) design. We create novel datasets, build AI models, and evaluate model performance and end-user impacts. When automated AI falls short, we design human-in-the-loop approaches supported by AI model explanations and creative user interfaces. To promote fair AI, we design better ways to annotate data without bias and modeling techniques to mitigate dataset biases. We conduct fundamental research, applied to real-world problems that matter, as part of UT Austin's Good Systems Grand Challenge to design responsible AI technologies. A theme of ongoing work is content moderation: automated, human-in-the-loop, and human-safe practices to curb disinformation, hate speech, and polarization online.
Research Areas:
Crowdsourcing & Human Computation (HCOMP) •
Fair & Explainable AI •
Information Retrieval (IR) •
Natural Language Processing (NLP)
Some recent publications and talks:
Other recent awards 🏆
Ripon Saha, Matthew Lease, Sarfraz Khurshid, and Dewayne Perry.
Improving Bug Localization using Structured Information Retrieval.
In IEEE/ACMConference on Automated Software Engineering (ASE), pages 345-355, 2013.
Postdocs
PhD Students
Anubrata Das (iSchool) [scholar, LinkedIn]
Soumyajit Gupta (Computer Science) [scholar, LinkedIn]
Chi-Yang (Ethan) Hsu (iSchool) [scholar, LinkedIn]
Gauri Kambhatla (Computer Science) [scholar, LinkedIn]
Houjiang Liu (iSchool) [scholar, LinkedIn]
Yiheng (Sam) Su (iSchool) [LinkedIn]
Selected Research & Demos
Houjiang Liu, Anubrata Das, Alexander Boltz, Didi Zhou, Daisy Pinaroc, Matthew Lease, and Min Kyung Lee. Human-centered NLP Fact-checking: Co-Designing with Fact-checkers using Matchmaking for AI. Proceedings of the ACM on Human-Computer Interaction, 2024. Presented at the 28th ACM Conference on Computer Supported Cooperative Work (CSCW). Honorable Mention. [ pdf | preprint ]
Ruijiang Gao, Maytal Saar-Tsechansky, Maria De-Arteaga, Ligong Han, Min Kyung Lee, Wei Sun and Matthew Lease. Robust Human-AI Collaboration with Bandit Feedback. The Conference on Information Systems and Technology (CIST), 2022. Best Student Paper award. [ preprint | conference-website ]
Li Shi, Nilavra Bhattacharya, Anubrata Das, Matthew Lease, and Jacek Gwizdka. The Effects of Interactive AI Design on User Behavior: An Eye-tracking Study of Fact-checking COVID-19 Claims. In Proceedings of the 7th ACM SIGIR Conference on Human Information, Interaction and Retrieval (CHIIR), pages 315--320, 2022. [ pdf | demo | sourcecode | video | poster | preprint ]
Anubrata Das, Brandon Dang, and Matthew Lease. Fast, Accurate, and Healthier: Interactive Blurring Helps Moderators Reduce Exposure to Harmful Content. In Proceedings of the 8th AAAI Conference on Human Computation and Crowdsourcing (HCOMP), pages 33--42, 2020. [ pdf | demo | blog-post | sourcecode | video | slides ]
Mucahid Kutlu, Tyler McDonnell, Tamer Elsayed, and Matthew Lease. Annotator Rationales for Labeling Tasks in Crowdsourcing. Journal of Artificial Intelligence Research (JAIR), 69:143--189, 2020. Award Winning Papers Track. [ pdf | blog-post | data | conference-website ]
Soumyajit Gupta, Mucahid Kutlu, Vivek Khetan, and Matthew Lease. Correlation, Prediction and Ranking of Evaluation Metrics in Information Retrieval. In Proceedings of the 41st European Conference on Information Retrieval (ECIR), pages 636--651, 2019. Best Student Paper award. [ news | pdf | data | sourcecode | slides | preprint ]
An Thanh Nguyen, Aditya Kharosekar, Aditya Kharosekar, Saumyaa Krishnan,
Siddhesh Krishnan, Elizabeth Tate, Byron C. Wallace, and Matthew Lease.
Believe it or not: Designing a Human-AI Partnership for
Mixed-Initiative Fact-Checking.
In Proceedings of the 31st ACM User Interface Software and
Technology Symposium (UIST), pages 189--199, 2018.
[ pdf |
demo |
sourcecode |
video |
slides ]
Tyler McDonnell, Matthew Lease, Mucahid Kutlu, and Tamer Elsayed. Why Is That Relevant? Collecting Annotator Rationales for Relevance Judgments. In Proceedings of the 4th AAAI Conference on Human Computation and Crowdsourcing (HCOMP), pages 139--148, 2016. Best Paper Award. [ news | pdf | blog-post | data | slides ]
Hyun Joon Jung and Matthew Lease. A Discriminative Approach to Predicting Assessor Accuracy. In Proceedings of the 37th European Conference on Information Retrieval (ECIR), pages 159--171, 2015. Samsung Human-Tech Paper Award: Silver Prize in Computer Science. [ pdf | news ]
Selected Talks: Videos and Slides (videos link is most current content)
Panel: Fair & Transparent AI: Lessons from UT Austin's Good Systems Grand Challenge (April 20, 2021)
Talk: Reducing Psychological Impacts of Content Moderation Work. UT Austin's Good Systems: Future of Work seminar series (Feb. 8, 2021)
Talk: Toward Safer Content Moderation and Better Supporting Complex Annotation Tasks Delft University speaker series on "Crowd Computing & ¡ AI" (The Academic Fringe Festival (Nov. 23, 2020)
Interview: Curbing misinformation, with help from the Micron Foundation (November 4, 2019)
Panel: Army Mad Scientist Day -- Ethics & the Future of AI Innovation (April 25, 2019)
Selected News
Recent honors and awards for Amazon scientists (additional coverage of AAAI Senior Member award, Amazon (April 20, 2023)
Announcement of AAAI Senior Member Status (January 3, 2023)
Recent honors and awards for Amazon scientists (additional coverage of ACM Distinguished Member award, Amazon, December 23, 2022)
Exploring Annotator Rationales for Active Learning with Transformers (UTCS, Dec. 14, 2022)
ACM Honors 2022 Distinguished Members (ACM, December 7, 2022)
Exploring Methods to Improve the Psychological Wellness of Content Moderators (UTCS, March 7, 2022)
An American gig work app was accused of working for Russia. Why? (NBC News, March 3, 2022)
Texas Researchers Pivot to Covid-19 (September 25, 2020)
TACC Covid-19 Twitter Dataset Enables Social Science Research about Pandemic (May 4, 2020)
Good Systems research on misinformation & fair AI (July 29, 2019)
Misinformation grant from Micron Foundation (May 29, 2019)
Press: Austin Statesman article Russian bots and the Austin bombings: Can fact-checking offset division, misinformation? (March 28, 2018). Read about our AI + Crowd system for checking online claims (AAAI 2018).
ALUMNI 🎓
Postdocs
Mucahid Kutlu (scholar, LinkedIn), 2018, Assistant Professor, Dept. of Computer Science and Engineering, Qatar University
Ph.D. Students
An Thanh Nguyen, 2020
Ye Zhang, 2019, Google
Hyunjoon Jung, 2015, Adobe
Masters Students
Utkarsh Mujumdar (iSchool), 2023, Autonomize AI. Thesis: Designing a Multi-Perspective Search System Using Large Language Models and Retrieval Augmented Generation. Winner: Dean's Choice Award.
Yian Wong (Computer Science), 2023, CenterPoint Energy. Thesis: Exploring Multiple Perspectives to Mitigate Cognitive Biases through an Integrated Interface to Language Model.
Sooyong Lee (Computer Science), 2023, UMass CS PhD Program. Thesis: Multi-Task Learning for Hate Speech Detection.
Yiheng (Sam) Su (Computer Science), 2023, iSchool PhD Program. Thesis: Wrapper Boxes for Increasing Model Interpretability via Example-based Explanations.
Sukanya Thapa (iSchool), 2023, Lazaza. Thesis: Enhancing Worker Management and Supporting External Tasks in Crowdsourced Data Labeling.
(2019-2022 to be posted...)
Vivek Pradhan, 2018, Earthmetry
Tyler McDonnell, 2017, SparkCognition
Ivan Oropeza, 2015, Google
Haofeng Zhou, 2015, Facebook
Shruti Bhosale, 2014, Facebook
Hohyon Ryu, 2012, OXOpolitics
Aashish Sheshadri, 2014, PayPal
Donna Vakharia, 2014, PayPal
Undergraduate Students (selected)
Qiwei (Renee) Li, 2019, Michigan PhD Program. Thesis: Clickbait and Emotional Language in Fake News
