The goal of the PASTEL project is to develop evience-based methods for efficient and practical learning engineering. In particular, we are interested in developing advanced technologies to build adaptive online courseware. The current PASTEL (Pragmatic methods to develop Adaptive and Scalable Technologies for next generation E-Learning) contains following methods:
- SMART (Skill Model mining with Automated detection of Resemblance among Texts) - An application of text mining for automatic discovery of latent skill model (a set of skills and concepets to be learned) from written instructional materials including text instructions, formative assessments, and hint meessages.
- RAFINE (Reinforcement learning Application For INcremental courseware Engineering) - An application of Reinforcement Leanring to automatically validate the online courseware contents based on students' performance and learning data.
- QUADL (QUiz generation with Application of Deep Learning) - An application of deep learning to automatically generate formative assessments from written instructions.
- WATSON (Web-based Authoring Technique for adaptive tutoring System on Online courseware) - An application of interactive machin learning to create intelligent tutoring systems (aka cognitive tutors) on a standard web-browser (hence easily embedded into the online courseware).
- RADARS (RApid Detection And Recovery from wheel Spinning) - An application of educational data-mining for early predication of unproductive failure (aka wheel-spinning) on particular online courseware.
Shimmei, M.*, & Noboru, M. (2019). Evidence-Based Recommendation for Content Improvement UsingReinforcementLearning. In S. Isotani, A. Ogan, B. McLaren, E. Millán, P. Hastings & R. Luckin (Eds.), Proceedings of the International Conference on Artificial Intelligence in Education (pp. 369-373). Cham, Switzerland: Springer.
Matsuda, N., Van Velsen, M., Barbalios, N., Lin, L., Vasa, H., Hosseini, R., . . . Bier, N. (2016). Cognitive Tutors Produce Adaptive Online Course: Inaugural Field Trial. In A. Micarelli, J. Stamper & K. Panourgia (Eds.), Proceedings of the International Conference on Intelligent Tutoring Systems (pp. 327-333). Switzerland: Springer. [0.27 acceptance rate out of 119 submissions]
Matsuda, N., Chandrasekaran, S., & Stamper, J. (2016). How quickly can wheel spinning be detected? In T. Barnes, M. Chi & M. Feng (Eds.), Proceedings of the International Conference on Educational Data Mining (pp. 607-608).
Matsuda, N., Furukawa, T., Bier, N., & Faloutsos, C. (2015). Machine beats experts: Automatic discovery of skill models for data-driven online course refinement. In J. G. Boticario, O. C. Santos, C. Romero, M. Pechenizkiy, A. Merceron, P. Mitros, J. M. Luna, C. Michaescu, P. Moreno, A. Hershkovitz, S. Ventura & M. C. Desmarais (Eds.), Proceedings of the International Conference on Educational Data Mining (pp. 101-108). Madrid, Spain.
Workshops, Symposiums, and other Conferences
Matsuda, N., & Shimmei, M.* (2019). Application of Reinforcement Learning For Automated Contents Validation Towards Self-Improving Online Courseware. In B. Goldberg (Ed.), Proceedings of the Annaul GIFT User Symposium (pp. 57-65). Orlando, FL: U.S. Army Combat Capabilities Development Command Soldier Center.
Park, S.*, & Matsuda, N. (2018). A Scalable Method for Rapid and Efficient Skill Discovery for Next-Generation Adaptive Online Courseware Paper presented at the Annual Meeting of the American Educational Research Association. New York, NY.
Shen, S.*, Shimmei, M.*, Chi, M., & Matsuda, N. (2019). Applications of Reinforcement Learning to Self-Improving Educational Systems. In A. M. Sinatra, A. C. Graesser, X. Hu, K. Brawner & V. Rus (Eds.), Design Recommendations for Intelligent Tutoring Systems (Vol. 7: Self-Improving Systems, pp. 77-96). Orlando, FL: US Army Research Lab.
National Science Foundation, Cyberlearning and Future Learning Technologies. Exploratory study on the Adaptive Online Course and its implication on synergetic competency. August 1, 2016 to July 31, 2018. Award No. 1623702. $550,000
National Science Foundation, Research on Education and Learning (DIR). Data-Driven Methods to Improve Student Learning from Online Courses. August 1, 2014 to July 31, 2017. Award No. 1418244. $504,740.