This research line explores human-inspired models of concept formation. Unlike most ML work, which emphasizes batch processing over structure-less vectors, I emphasize the incremental acquisition of structured concepts from a continuous stream of experiences.

The primary output of this work has been the concept formation library for python.

Computational Modeling

MacLellan, C.J., Harpstead, E., Aleven, V., Koedinger K.R. (2016) TRESTLE: A Model of Concept Formation in Structured Domains. Advances in Cognitive Systems, 4, 131-150. (pdf)

Unger, L., Fisher, A. V., & MacLellan, C.J. (2014) Developmental Changes in the Semantic Organization of Living Kinds. In P. Bello, M. Guarini, M. McShane, & B. Scassellati (Eds.), Proceedings of the 36th Annual Meeting of the Cognitive Science Society (pp. 1646-1651). Quebec City: Cognitive Science Society. (pdf)

Modeling Applications

Harpstead, E. , MacLellan, C. J., Aleven, V., Myers, B. A. (2015). Replay analysis in open-ended educational games. In C. S. Loh, Y. Sheng, and D. Ifenthaler (Eds.), Serious Game Analytics: Methodologies for Performance Measurement, Assessment, and Improvement, 381-399. Switzerland: Springer International. doi: 10.1007/978-3-319-05834-4_17

Harpstead, E., MacLellan, C.J., Aleven, V. (2015). Discovering Knowledge Models in an Open-Ended Educational Game using Concept Formation. In J. Boticario & K. Muldner (Eds.), Proceedings of the Workshops at the 17th International Conference on Artificial Intelligence in Education AIED 2015 (Vol. 2, pp. 9-16). Aachen: CEUR-WS.org. (pdf)

Harpstead, E., MacLellan, C.J., Aleven, V., & Koedinger, K.R. (2014). Using Data to Explore the Differences between Instructional Vision and Student Performance. In Learning Innovations at Scale CHI 2014 Workshop. (pdf)

Harpstead, E., MacLellan, C.J., Aleven, V., Myers, B.A. (2014) Using Extracted Features to Inform Alignment-Driven Design Ideas in an Educational Game. In A. Schmidt & T. Grossman (Eds.), Proceedings of the 32nd Annual SIGCHI Conference on Human Factors in Computing Systems—CHI ‘14 (pp. 3329–3338). New York: ACM Press. doi: 10.1145/2556288.2557393 (pdf)

Harpstead, E., MacLellan, C.J., Koedinger, K.R., Aleven, V., Dow, S.P., Myers, B.A. (2013) Investigating the Solution Space of an Open-Ended Educational Game Using Conceptual Feature Extraction. In S.K. D’Mello, R.A. Calvo, & A. Olney (Eds.), Proceedings of the 6th International Conference on Educational Data Mining (pp. 51-58). Memphis, TN: International Educational Data Mining Society (pdf)