About
Dr. Pan is an Associate Professor at the Information Systems Department of UMBC. Before joining UMBC, Dr. Pan was a research scientist at IBM Watson Research Center. Her research interests include Natural Language Processing (NLP), Social Media Analytics, Bias and Fairness in AI and Human-AI Interaction. Dr. Pan has served on the program committees of major international conferences (e.g., ACL, EMNLP, NAACL, IJCAI). She was the program chair of 2015 and conference chair of 2019 ACM IUI. She was the program chair of IEEE ICTAI 2020. Currently, she is an associate editor of ACM Transactions on Interactive Intelligent Systems (TIIS) and a member of the steering committee of IUI. Dr. Pan received a Ph.D. in Computer Science from Columbia University
Research interests
Natural Language Processing (NLP), Social Media Analytics , Artificial Intelligence (AI), Machine Learning (ML), Big Data, Computational Social Science, Computational Psychology, Speech Processing, Dialogue Systems, Fair AI and Machine Learning, Human-AI Interaction, User Modeling and Personalization.
Teaching interests
Artificial Intelligence (AI), Natural Language Processing (NLP), Social Media Analytics, Information Extraction (IE), Machine Learning (ML), Data Mining (DM) and Database Systems.
Education
-
Ph D, Computer Science
— Columbia University (2002) Prosody Modeling for Concept to Speech Generation
- Other, Computer Science — Columbia University (1998)
-
BS, Computer Science
— Tsinghua University (1991) Corpus-based Chinese Parsing
Publications
- Developing Problem-Solving Competency in Data Science: Exploring A Case-Based Approach 2025
- Can generative AI be egalitarian? 2024
- RAGged edges: the double-edged sword of retrieval-augmented chatbots 2024
- When Biased Humans Meet Debiased AI: A Case Study in College Major Recommendation 2023
- Do humans prefer debiased AI algorithms? A case study in career recommendation 2022
- Causal feature selection with dimension reduction for interpretable text classification 2022
- Machine Learning and Student Performance in Teams 2020
- An Intersectional Definition of Fairness 2020
- Mitigating Socio-lingustic Bias in Job Recommendation 2020
- Differential Fairness 2019
- Fair inference for discrete latent variable models
- Tell me something that will help me trust you: A survey of trust calibration in human-agent interaction
- Polling latent opinions: A method for computational sociolinguistics using transformer language models
- An Intersectional Definition of Fairness
Presentations
- Can Generative AI be Egalitarian? 2025
- SDM 2023 tutorial: “How to Design a Fair Data Mining System: Navigating the Trade-Offs,” April 2023 2023
- Differential Fairness for Machine Learning and Artificial Intelligence Systems: Unbiased Decisions with Biased Data 2018
Grants and Contracts
- AI-DCL: Fairness for the Allocation of Healthcare Resources 2019
- Assessing the Reliability and Robustness of Generative AI: Humans and AI Each Hold up Half the Sky
- III: Small: Social Media-based Large Scale Personal Persuasion
- NSF-CSIRO: Analyzing and Mitigating Sociolingustic AI-Bias (SLAB) in Natural Language Processing
- Video Storytelling with Generative Adversarial Networks