Student learning strategies and behaviors to predict success in an online adaptive mathematics tutoring system
Abstract
Student learning strategies play a critical role in their overall success. The central goal of this study is to investigate how learning strategies are related to student success in an online adaptive mathematics tutoring system. To accomplish this goal, we developed a model to predict student performance based on their strategies in ALEKS, an online learning environment. We have identified student learning strategies and behaviors in seven main categories: help-seeking, multiple consecutive errors, learning from errors, switching to a new topic, topic mastery, reviewing previous mastered topics, and changes in behavior over time. The model, developed by using stepwise logistic regression, indicated that requesting two consecutive explanations, making consecutive errors and requesting an explanation, and changes in learning behaviors over time, were associated with lower success rates in the semester-end assessment. By contrast, the reviewing previous mastered topics strategy was a positive predictor of success in the last assessment. The results showed that the predictive model was able to predict students’ success with reasonably high accuracy.
Publication Title
Proceedings of the 10th International Conference on Educational Data Mining, EDM 2017
Recommended Citation
Xie, J., Mojarad, S., Shubeck, K., Essa, A., Baker, R., & Hu, X. (2017). Student learning strategies and behaviors to predict success in an online adaptive mathematics tutoring system. Proceedings of the 10th International Conference on Educational Data Mining, EDM 2017, 460-465. Retrieved from https://digitalcommons.memphis.edu/facpubs/8635
