One well-known study using educational data mining is Baker, R. & Yacef, K. (2009), which analyzes student interaction data from intelligent tutoring systems to predict learning behaviors such as engagement, gaming the system, and misconceptions. Their research shows that EDM can identify patterns in student behavior, forecast performance, and detect which activities lead to deeper learning.

However, educational data mining cannot fully explain why students behave a certain way, nor can it capture emotional states, motivation, or the quality of student thinking unless paired with qualitative data. It reveals patterns, but not the full complexity of human learning.

References

Baker, R. S., & Yacef, K. (2009). The state of educational data mining in 2009: A review and future visions. Journal of Educational Data Mining.

Pardos, Z. A., & Heffernan, N. T. (2011). KT-IDEM: Introducing item difficulty to knowledge tracing. Proceedings of the 4th International Conference on Educational Data Mining.