TY - GEN
T1 - Mining and Assessing Anomalies in Students’ Online Learning Activities with Self-supervised Machine Learning
AU - Jiang, Lan
AU - Bosch, Nigel
N1 - Publisher Copyright:
© 2022 Copyright is held by the author(s).
PY - 2022
Y1 - 2022
N2 - Two students in the same course working toward the same learning objectives may have very different strategies. However, on average, there are likely to be some patterns of student actions that are more common than others, especially when students are implementing typical self-regulated learning strategies. In this paper, we focus on distinguishing between students’ typical actions and unusual, anomalous sequences of actions. We define anomalous activities as unexpected activities given a student’s preceding activities. We distinguish these anomalies by training a self-supervised neural network to determine how predictable activities happen (the complement of which are anomalies). A random forest model trained to predict course grades from anomaly-based features showed that anomalous actions were significant predictors of course grade (mean Pearson’s r = .399 across 7 courses). We also explore whether humans regard the anomalous activities labeled by the model as anomalies by asking people to label 20 example sequences. We further discuss the implications of our method and how detecting and understanding anomalies could potentially help improve students’ learning experiences.
AB - Two students in the same course working toward the same learning objectives may have very different strategies. However, on average, there are likely to be some patterns of student actions that are more common than others, especially when students are implementing typical self-regulated learning strategies. In this paper, we focus on distinguishing between students’ typical actions and unusual, anomalous sequences of actions. We define anomalous activities as unexpected activities given a student’s preceding activities. We distinguish these anomalies by training a self-supervised neural network to determine how predictable activities happen (the complement of which are anomalies). A random forest model trained to predict course grades from anomaly-based features showed that anomalous actions were significant predictors of course grade (mean Pearson’s r = .399 across 7 courses). We also explore whether humans regard the anomalous activities labeled by the model as anomalies by asking people to label 20 example sequences. We further discuss the implications of our method and how detecting and understanding anomalies could potentially help improve students’ learning experiences.
KW - Anomalies
KW - Human understanding of anomalies
KW - Log activities
UR - http://www.scopus.com/inward/record.url?scp=85174842778&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85174842778&partnerID=8YFLogxK
U2 - 10.5281/zenodo.6852948
DO - 10.5281/zenodo.6852948
M3 - Conference contribution
AN - SCOPUS:85174842778
T3 - Proceedings of the 15th International Conference on Educational Data Mining, EDM 2022
BT - Proceedings of the 15th International Conference on Educational Data Mining, EDM 2022
PB - International Educational Data Mining Society
T2 - 15th International Conference on Educational Data Mining, EDM 2022
Y2 - 24 July 2022 through 27 July 2022
ER -