The AskOski Project seeks to improve equity and achievement in higher education by making colleges and universities first-class beneficiaries of human-centered AI research.

AskOski, named after Cal's sports mascot, is a personalized academic exploration and degree planning system that collects various University data into a central platform allowing students to illuminate the academic terrain of their institution like never before. The system incorporates degree audit, course description, class schedule, future course preferences, and historic enrollment information combined with machine learning to help students explore their interests, connect course concepts across departments and draw up plans for future semesters while satisfying constraints of their programs.

This system is a product of ongoing research in data science, education, and cognition conducted by the Computational Approaches to Human Learning (CAHL) research lab. It is not meant to replace academic advising but rather allow students to benefits from the course pathways taken by students with similar course histories and majors and explore topical relationships between courses as informed by their peers. In this sense, the recommendations provided are not objective, but rather an alternative source of perspective on the conceptual landscape of the university which we hope students find informative.

Projects in learning analytics, such as this one, require the engagement of a cross-campus community. Our research is supported by grants from the National Science Foundation (#1547055 and #1446641) and Schmidt Futures. The system's data feeds are made possible by Enterprise Data & Analytics (ED&A) with approval and feedback from the UC Berkeley Office of the Registrar (OR). User studies conducted for research purposes have been approved by an Internal Review Board where deemed necessary by the UC Berkeley Committee for Protection of Human Subjects. We thank the following UCB staff and leadership for their essential past and continuing support: Andrew Eppig (OPA), Sanghamithra Bandi (ED&A), Radha Karichedu (ED&A), Aswan Movva (ED&A), Anji Gannavarapu (EDW), Mark Chiang (ex-EDW), Daniel Grieb (RTL), Raul Infante (OR), Max Michel (ex-ED&A), Jenn Stringer (CIO), Larry Conrad (ex-CIO), Johanna Metzgar (ex-OR), and Walter Wong (Registrar).

• Lekan, K., Pardos, Z.A. (2023) AI-Augmented Advising: A Comparative Study of ChatGPT-4 and Advisor-based Major Recommendations. Presented at the Generative AI for Education Workshop (GAIED) at the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS). New Orleans, LA.
• Xu, L., Pardos, Z. A., & Pai, A. (2023). Convincing the Expert: Reducing Algorithm Aversion in Administrative Higher Education Decision-making. In Proceedings of the Tenth ACM Conference on Learning@ Scale. Copenhagen, DK. ACM. Pages 215-225.
• Kizilcec, R.F., Baker, R.B., Bruch, E., Cortes, K.E., Hamilton, L.T., Lang, D.N., Pardos, Z.A., Thompson, M.E., Stevens, M.L. (2023). From pipelines to pathways in the study of academic progress. Science, 380, 344-347.
• Borchers, C., & Pardos, Z. A. (2023). Insights into undergraduate pathways using course load analytics. In Proceedings of the 14th International Learning Analytics and Knowledge Conference (LAK). ACM. Pages 219–229. Best Paper Honorable Mention
• Pardos, Z. A., Borchers, C., & Yu, R. (2023). Credit hours is not enough: Explaining undergraduate perceptions of course workload using LMS records The Internet and Higher Education, 53, 100882.
• Shao, E., Guo, S., & Pardos, Z.A. (2021) Degree Planning with PLAN-BERT: Multi-Semester Recommendation Using Future Courses of Interest. In Proceedings of the AAAI Conference on Artificial Intelligence, 35 (17), 14920-14929.
• Jiang, W., Pardos, Z.A. (2021) Towards Equity and Algorithmic Fairness in Student Grade Prediction. In B. Kuipers, S. Lazar, D. Mulligan, & M. Fourcade (Eds.) Proceedings of the Fourth AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society.
• Cockkalingam, S., Yu, R., Pardos, Z.A. (2021) Which one's more work? Predicting effective credit hours between courses. In N. Dowell, S. Joksimovic, M. Scheffel, & G. Siemens (Eds.) Proceedings of the 11th International Conference on Learning Analytics and Knowledge (LAK). ACM.
• Yu, R., Pardos, Z.A., Chau, H., Brusilovsky, P. (2021) Orienting Students to Course Recommendations Using Three Types of Explanation. In Adjunct Proceedings of the 29th Conference on User Modeling, Adaptation and Personalization (UMAP). Pages 238–245.
• Pardos, Z.A., Nam, A.J.H. (2020) A university map of course knowledge. PLoS ONE 15(9): e0233207.
• Jiang, W., Pardos, Z. A. (2020) Evaluating sources of course information and models of representation on a variety of institutional prediction tasks. In A. Rafferty and J.R. Whitehill (Eds.) Proceedings of the 13th International Conference on Educational Data Mining (EDM). Pages 115-125.
• Pardos, Z.A., Jiang, W. (2020) Designing for Serendipity in a University Course Recommendation System. In K. Verbert, M. Scheffel, N. Pinkwart, & V. Kovanovic (Eds.) Proceedings of the 10th International Conference on Learning Analytics and Knowledge (LAK). ACM. Pages 350–359.
• Pardos, Z.A., Fan, Z., Jiang, W. (2019) Connectionist Recommendation in the Wild: On the utility and scrutability of neural networks for personalized course guidance. User Modeling and User-Adapted Interaction, 29(2), 487–525.
• Pardos, Z. A., Chau, H., Zhao, H. (2019) Data-Assistive Course-to-Course Articulation Using Machine Translation. In J. C. Mitchell & K. Porayska-Pomsta (Eds.) Proceedings of the 6th ACM Conference on Learning @ Scale (L@S). Chicago, IL. ACM.
• Pardos, Z.A., & Jiang, W. (2019) Combating the Filter Bubble: Designing for Serendipity in a University Course Recommendation System. CoRR preprint, abs/1907.01591. Workshop versions: [RecSys/IntRS][KDD/DL4E]
• Jiang, W., Pardos, Z.A., Wei, Q. (2019) Goal-based Course Recommendation. In C. Brooks, R. Ferguson & U. Hoppe (Eds.) Proceedings of the 9th International Conference on Learning Analytics and Knowledge (LAK 2019). ACM. Tempe, Arizona. Pages 36-45. [slides]
• Jiang, W., Pardos, Z.A. (2019) Time Slice Imputation for Personalized Goal-based Recommendation in Higher Education. In D. Tikk & P. Brusilovsky (Eds.) Proceedings of the 13th ACM Conference on Recommender Systems. Copenhagen, Denmark. ACM.
• Dong, M., Yu, R., Pardos, Z.A. (2019) Design and Deployment of a Better Course Search Tool: Inferring latent keywords from enrollment networks. In M. Scheffel & J. Broisin (Eds.) Proceedings of the 14th European Conference on Technology Enhanced Learning (EC-TEL). Delft, The Netherlands. Springer. Pages 480-494.
• Alkaoud, M., & Pardos, Z. A. (2019). Degree Curriculum Contraction: A Vector Space Approach. In International Conference on Artificial Intelligence in Education. Pages 14-18. Springer, Cham.
• Luo, Y., Pardos, Z.A. (2018) Diagnosing University Student Subject Proficiency and Predicting Degree Completion in Vector Space. In E. Eaton & M. Wollowski (Eds.) Proceedings of the 33rd Conference on Advances in Artificial Intelligence (AAAI). New Orleans, LA. AAAI Press. Pages 7920-7927. [slides]
• One-page flyer describing the system