Abstract
This paper explores the relationship between student performance on online programming exercises completed during semester with subsequent student performance on a final exam. We introduce an approach that combines whether or not a student produced a correct solution to an online exercise with information on the number of attempts at the exercise submitted by the student. We use data collected from students in an introductory Java course to assess the value of this approach. We compare the approach that utilizes the number of attempts to an approach that simply considers whether or not a student produced a correct solution to each exercise. We found that the results for the method that utilizes the number of attempts correlates better with performance on a final exam.
Original language | English |
---|---|
Title of host publication | ITiCSE 2016 |
Subtitle of host publication | Proceedings of the 2016 ACM Conference on Innovation and Technology in Computer Science Education |
Place of Publication | New York, NY |
Publisher | Association for Computing Machinery |
Pages | 218-223 |
Number of pages | 6 |
ISBN (Electronic) | 9781450342315 |
DOIs | |
Publication status | Published - 2016 |
Externally published | Yes |
Event | 2016 ACM Conference on Innovation and Technology in Computer Science Education, ITiCSE 2016 - Arequipa, Peru Duration: 11 Jul 2016 → 13 Jul 2016 |
Conference
Conference | 2016 ACM Conference on Innovation and Technology in Computer Science Education, ITiCSE 2016 |
---|---|
Country/Territory | Peru |
City | Arequipa |
Period | 11/07/16 → 13/07/16 |
Keywords
- educational data mining
- learning analytics
- programming