zachpardos.jpg

Zachary Pardos

Assistant Professor (I School and Graduate School of Education)

South Hall #211 & 2121 Berkeley Way #4232
Fridays 12:30-1:30pm @ https://berkeley.zoom.us/my/pardos

Focus

Learning Analytics, Digital Learning Environments, Machine Learning

Research areas

Biography

Dr. Pardos is an Assistant Professor at UC Berkeley in the School of Information and Graduate School of Education. His focal areas of study are knowledge representation and personalized supports leveraging big data in education. He earned his PhD in Computer Science at WPI and comes to UC Berkeley after a post-doc at MIT Computer Science Artificial Intelligence Lab (CSAIL). At UC Berkeley he directs the Computational Approaches to Human Learning (CAHL) research lab and teaches courses on data mining and analytics, digital learning environments, and machine learning in education.

Most recent work (2017-2018):

Journal pre-prints:

Pardos, Z.A., Fan, Z., Jiang, W. (2018) Connectionist Recommendation in the Wild. CoRR preprint, abs/1803.0953. [arXiv]

Pardos, Z.A., Horodyskyj, L. (2017) Analysis of Student Behaviour in Habitable Worlds Using Continuous Representation Visualization. CoRR preprint, abs/1710.06654. [arXiv]

Published:

Pardos, Z.A., Dadu, A. (In-press) dAFM: Fusing Psychometric and Connectionist Modeling for Q-matrix Refinement. To appear in the Journal of Educational Data Mining. [pdf] [slides] [code]

Pardos, Z.A., Hu, C., Meng, P., Neff, M., and Abrahamson, D. (2018). Classifying Learner Behavior from High Frequency Touchscreen Data Using Recurrent Neural Networks. In D. Chin & L. Chen (Eds.) Adjunct Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization (UMAP). Singapore. ACM. Pages 317-322. [pdf]

Le, C.V., Pardos, Z.A., Meyer, S.D., Thorp, R. (2018) Communication at Scale in a MOOC Using Predictive Engagement Analytics. In M. Mavrikis, K. Porayska-Pomsta & R. Luckin (Eds.) Proceedings of the 19th International Conference on Artificial Intelligence in Education (AIED). London, UK. Pages 239-252. [html] [pdf] [slides] [code]

Pardos, Z.A., Farrar, S., Kolb, J., Peh, G.X., Lee, J.H. (2018) Distributed Representation of Misconceptions. In J. Kay & R. Luckin (Eds.) Proceedings of the 13th International Conference of the Learning Sciences (ICLS). London, UK. Pages 1791-1798. [pdf] [slides]

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 Eighth AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI). New Orleans, LA. AAAI Press. Pages 7920-7927. [pdf] [slides]

Pardos, Z.A. (2017) Big Data in Education and the Models that Love Them. Current Opinion in Behavioral Sciences. Vol 18, 107-113. [html]

Pardos, Z.A., Dadu, A. (2017) Imputing KCs with Representations of Problem Content and Context. In F. Cena & M. Desmarais (Eds.) Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization (UMAP). Bratislava, Slovakia. ACM. Pages 148-155. [acm] [slides]

Pardos, Z.A., Tang, S., Davis, D., Le. C.V. (2017) Enabling Real-Time Adaptivity in MOOCs with a Personalized Next-Step Recommendation Framework. In C. Thille & J. Reich (Eds.) Proceedings of the 4th Conference on Learning @ Scale (L@S). ACM. Pages 23-32. [acm] [slides]

Pardos, Z. A., & Nam, A. J. H. (2017) The iSchool of Information and its Relationship to Computer Science at UC Berkeley. In W. Shim & C. Chen (Eds.) iConference Proceedings. Wuhan, China. Pages 309-316. [pdf] [slides]

Tang, S., Peterson, J., and Pardos, Z. (2017) Predictive Modelling of Student Behaviour Using Granular Large-Scale Action Data. In C. Lang, G. Siemens, A.F. Wise& D. Gaevic (Eds.) The Handbook of Learning Analytics, Pages 223–233. Society for Learning Analytics Research (SoLAR), Alberta, Canada, 1st edition. [pdf]

Sharma, K., Jermann, P., Dillenbourg, P., Rau, M., Pardos, Z. A., Schneider, B., D’Angelo, S., Gergle, D., & Prieto, L. (2017) CSCL and Eye-tracking: Experiences, Opportunities and Challenges. In B. K. Smith, M. Borge, E. Mercier & K. Y. Lim (Eds.) Proceedings of the 12th International Conference on Computer Supported Collaborative Learning (CSCL). Philadelphia, PA. Vol. 2, 727-734. [isls]

For a full publication list please consult my Google [scholar page] or my CV.

Active Research Grants

(NSF IIS) Deep Learning in Higher Education Big Data to Explore Latent Student Archetypes and Knowledge Profiles [2015-present]

(NSF DRK-12) Personalizing Recommendations in a Large-Scale Education Analytics Pipeline [2015-present]

(Google) Scaling Cognitive Modeling to Massive Open Environments [2014-present]

General areas:

- Representing knowledge as communicated by student behaviors
- Personalized educational supports leveraging learner process data
- Digital Learning Environments (online courses and Intelligent Tutoring Systems)

I am currently accepting PhDs (in Education and the iSchool). Consult tiny.cc/zpUCB to schedule a meeting. 

Select Service / Professional Activities

  • Director of Computational Approaches to Human Learning (CAHL) Research Lab: https://github.com/CAHLR
  • Director of the on-campus learning analytics project, AskOski [learn more]
  • Artificial Intelligence in Education Executive committee
  • Program committee member (2018): AIED, EDM, ICLS, ITS, L@S, LAK
  • EAAI New and Future AI Educator (2018)
  • Editorial Board – Journal of Educational Data Mining & Int. Journal of AI in Education
  • Panelist/speaker - National Academy of Education: Big Data and Privacy (2016): http://naeducation.org/bigdata
  • Program co-chair of the 2014 Educational Data Mining Conference
  • Community Liaison for the International Educational Data Mining Society
  • Panelist - White House/OSTP: Big Data and Privacy Workshop, Berkeley (2014)
  • Co-keynote/seminar speaker: ACT, Educational Testing Service, Intel Adaptive Education
  • Joint Campus Committee on Information Technology (JCCIT), 2016-2017
  • Asiomar Highered Convention: http://asilomar-highered.info/

Teaching

INFO 254: Data Mining and Analytics (every Spring) [syllabus]
INFO/EDU C260F: Machine Learning in Education (every Fall) [syllabus][page]
WEDUC 161: Digital Learning Environments (every Fall - online, UC wide ) [syllabus][website]
EDUC 290A/003: Computational Approaches to Human Learning (CAHL) research group (every semester) [website]

Research group class info: This group will be run as a platform for discussions on topics ranging from analysis of equity, diversity, and inclusion on campus to the role of AI in K-16 education. After the first meeting brainstorming session (and food), a list of topics will be developed that students can choose from to discuss during one meeting of class. The second expected contribution is that each student use one meeting to present work of theirs, related directly or tangentially to the group's research area. Except for the first and last meeting, the class will meet ONLINE (on Zoom) Wednesdays 11:30-1pm (CCN is 15555).

Education

Postdoctoral Associate, Physics & CSAIL - Massachusetts Institute of Technology
Doctor of Philosophy, Computer Science - Worcester Polytechnic Institute
Bachelors of Science, Computer Science - Worcester Polytechnic Institute

Last updated:

October 16, 2018