Identifying relevant user behavior, predicting learning, and persistence in an ITS-based afterschool program
Abstract
ALEKS (Assessment and Learning in Knowledge Spaces) has recently shown promise for effectively training mathematics at equivalent levels to human teachers. However, not much is known about how the system accomplished this. In this paper, we describe the use of three data mining techniques used to analyze student data from an afterschool program with ALEKS. Our first analysis used DMM modeling and k-clustering to identify important groups of behaviors within ALEKS users and to show the importance of context for elements. Our second analysis focused on identifying learner behaviors that predict student learning during the program. The final analysis presents a method for determine learner persistence within the afterschool program.
Publication Title
Proceedings of the 9th International Conference on Educational Data Mining, EDM 2016
Recommended Citation
Craig, S., Huang, X., Xie, J., Fang, Y., & Hu, X. (2016). Identifying relevant user behavior, predicting learning, and persistence in an ITS-based afterschool program. Proceedings of the 9th International Conference on Educational Data Mining, EDM 2016, 581-582. Retrieved from https://digitalcommons.memphis.edu/facpubs/8031
