Mahsa Bazzaz
PhD Student
Education
- BS in Computer Engineering, Amirkabir University of Technology — Iran
Biography
Mahsa Bazzaz is a doctoral candidate in the Khoury College of Computer Sciences at Northeastern University, based in Boston. She is advised by Seth Cooper.
Bazzaz focuses on human-centered AI, specifically how people perceive, interact with, and form expectations around AI-generated content. Her work draws on quantitative and qualitative approaches to understand user experience, with the goal of informing the design of more intuitive, trustworthy, and user-centered AI systems. Building on both her lifelong interest with games, much of her work explores procedural content generation and player experience.
Before joining Khoury College in 2023, Bazzaz completed her undergraduate studies in computer engineering at Amirkabir University of Technology, where she built a strong foundation in software engineering and AI. Since beginning her doctoral studies, she has also served as a teaching assistant in human–computer interaction, algorithms, and game programming courses at Khoury College.
In her free time, Bazzazz enjoys playing mystery puzzle games.
Recent publications
-
Playing the Imitation Game: How Perceived Generated Content Shapes Player Experience
Citation: Mahsa Bazzaz, Seth Cooper. (2026). Playing the Imitation Game: How Perceived Generated Content Shapes Player Experience CoRR, abs/2602.14254. https://doi.org/10.48550/arXiv.2602.14254 -
Analysis of Robustness of a Large Game Corpus
Citation: Mahsa Bazzaz, Seth Cooper. (2025). Analysis of Robustness of a Large Game Corpus FDG, 33:1-33:9. https://doi.org/10.1145/3723498.3723820 -
Stuck in the Middle: Generating Levels without (or with) Softlocks
Citation: Seth Cooper, Mahsa Bazzaz. (2025). Stuck in the Middle: Generating Levels without (or with) Softlocks FDG, 68:1-68:9. https://doi.org/10.1145/3723498.3723844 -
Sturgeon-MKIV: Constraint-Based Level and Playthrough Generation with Graph Label Rewrite Rules
Citation: Seth Cooper, Mahsa Bazzaz. (2024). Sturgeon-MKIV: Constraint-Based Level and Playthrough Generation with Graph Label Rewrite Rules AIIDE, 13-24. https://doi.org/10.1609/aiide.v20i1.31862
