Abstract
Self-regulated learning (SRL) is critical for teachers to gain a sophisticated understanding of technological pedagogical content knowledge (TPACK), which is needed to optimize the use of technologies in teaching. This research aims to discover teachers’ SRL processes from 70 participants. We apply educational data mining and learning analytics methods to mine teachers’ SRL processes using the computer logs extracted from nBrowser - a computer-based learning environment. The fuzzy mining algorithm of process mining is used to discover the temporal SRL process models. The conformance checking algorithm tests whether there is a significant difference in SRL patterns between teachers with different TPACK performance. The findings can contribute to the advancement of our scientific understanding of the role of SRL in teacher education and inform teacher educators and researchers about how to design scaffolds to support teachers’ regulation in complex technology-integrating tasks. Copyright © 2020 Society for Learning Analytics Research (SoLAR).
| Original language | English |
|---|---|
| Title of host publication | Companion Proceedings of the 10th International Learning Analytics and Knowledge Conference (LAK’20) |
| Publisher | Society for Learning Analytics Research (SoLAR) |
| Pages | 219-224 |
| Publication status | Published - Mar 2020 |
Citation
Huang, L., & Lajoie, S. P. (2020). Discovering teachers’ regulatory learning processes in technology integration using educational data mining approaches. In Companion Proceedings of the 10th International Learning Analytics and Knowledge Conference (LAK’20) (pp. 219-224). Society for Learning Analytics Research (SoLAR). https://www.solaresearch.org/core/lak20-companion-proceedings/Keywords
- Self-regulated learning
- Traces Methods
- Educational data mining
- Process mining