Abstract
Modern machine learning methods are critical to the development of large-scale personalized learning systems that cater directly to the needs of individual learners. The recently developed SPARse Factor Analysis (SPARFA) framework jointly estimates learner’s knowledge of the latent concepts underlying a domain and the relationships among a collection of questions and the latent concepts, solely from the graded responses to a collection of questions. To better interpret the estimated latent concepts, SPARFA relies on a post-processing step that utilizes user-defined tags (e.g., topics or keywords) available for each question. In this paper, we relax the need for user-defined tags by extending SPARFA to jointly process both graded learner responses and the text of each question and its associated answer(s) or other feedback. Our purely data-driven approach (i) enhances the interpretability of the estimated latent concepts without the need of explicitly generating a set of tags or performing a post-processing step, (ii) improves the prediction performance of SPARFA, and (iii) scales to large test/assessments where human annotation would prove burdensome. We demonstrate the efficacy of the proposed approach on two real educational datasets.
Original language | English (US) |
---|---|
Title of host publication | Proceedings of the 6th International Conference on Educational Data Mining, EDM 2013 |
Editors | Sidney K. D'Mello, Rafael A. Calvo, Andrew Olney |
Publisher | International Educational Data Mining Society |
ISBN (Electronic) | 9780983952527 |
State | Published - Jan 1 2013 |
Event | 6th International Conference on Educational Data Mining, EDM 2013 - Memphis, United States Duration: Jul 6 2013 → Jul 9 2013 |
Other
Other | 6th International Conference on Educational Data Mining, EDM 2013 |
---|---|
Country/Territory | United States |
City | Memphis |
Period | 7/6/13 → 7/9/13 |
ASJC Scopus subject areas
- Computer Science Applications
- Information Systems