PERC 2018 Abstract Detail Page
Previous Page | New Search | Browse All
Abstract Title: | Predicting on campus student performance from video interactions. |
---|---|
Abstract: | In this work, we attempted to predict student performance on a suite of laboratory activities from students' interactions with associated instructional videos. The students' performance is measured by a graded presentation for each of four laboratory exercises in an introductory physics course. Each lab exercise was associated with between one and three videos of instructional content. Using video clickstream data we define summary features (number of pauses, seeks) and contextual information (fraction of time played, in-semester order). These features serve as inputs to machine learning (ML) algorithms that aim to predict student performance on the laboratory exercise presentations. We explore the power of two ML algorithms: a support vector machine (SVM) and logistic regression (LR). Our findings show that SVM and LR models are unable to predict student performance. We compare our findings to findings from other studies and explore caveats to the null-result like the complexity of the assignment. |
Abstract Type: | Contributed Poster Presentation |
Session Time: | Poster Session I |
Poster Number: | A84 |
Contributed Paper Record: | Contributed Paper Information |
Contributed Paper Download: | Download Contributed Paper |
Author/Organizer Information | |
Primary Contact: |
Robert Solli University of Oslo Ole Moes vei 14 a Oslo, Non U.S. 1165 Phone: +4747393250 |
Co-Author(s) and Co-Presenter(s) |
John M. Aiken, Marcos D. Caballero |
Contributed Poster | |
Contributed Poster: | Download the Contributed Poster |