Predicting academic success based on learning material usage
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
Details
| Original language | English |
|---|---|
| Title of host publication | SIGITE 2017 - Proceedings of the 18th Annual Conference on Information Technology Education |
| Publisher | ACM |
| Pages | 13-18 |
| Number of pages | 6 |
| ISBN (Electronic) | 9781450351003 |
| DOIs | |
| Publication status | Published - 27 Sep 2017 |
| Publication type | A4 Article in a conference publication |
| Event | ANNUAL CONFERENCE ON INFORMATION TECHNOLOGY EDUCATION - Duration: 1 Jan 1900 → … |
Conference
| Conference | ANNUAL CONFERENCE ON INFORMATION TECHNOLOGY EDUCATION |
|---|---|
| Period | 1/01/00 → … |
Abstract
In this work, we explore students' usage of online learning material as a predictor of academic success. In the context of an introductory programming course, we recorded the amount of time that each element such as a text paragraph or an image was visible on the students' screen. Then, we applied machine learning methods to study to what extent material usage predicts course outcomes. Our results show that the time spent with each paragraph of the online learning material is a moderate predictor of student success even when corrected for student time-on-task, and that the information can be used to identify at-risk students. The predictive performance of the models is dependent on the quantity of data, and the predictions become more accurate as the course progresses. In a broader context, our results indicate that course material usage can be used to predict academic success, and that such data can be collected in-situ with minimal interference to the students' learning process.
ASJC Scopus subject areas
Keywords
- Academic success prediction, Educational data mining, Element-level web logs, Online learning materials, Web log mining