Explainable Deep Learning Framework for Understanding Distractions and Students’ Productivity Prediction
Sasikkala, K and Kalaichelvi, N Explainable Deep Learning Framework for Understanding Distractions and Students’ Productivity Prediction. Journal of Academic trends & innovative research, 2 (6): 1. pp. 1422-1424. ISSN 3139-8464
![[thumbnail of Explainable Deep Learning Framework for Understanding Distractions and Students’ Productivity Prediction]](https://ir.vistas.ac.in/style/images/fileicons/text.png)
Text (Explainable Deep Learning Framework for Understanding Distractions and Students’ Productivity Prediction)
Published Paper.pdf - Published Version
Download (292kB)
Abstract
Abstract—Student productivity is influenced by digital, behavioral, environmental, and
psychological distractions. This paper proposes an Explainable Deep Learning Framework
(XDLF) integrating LSTM, SHAP, and LIME to predict productivity and explain
influential factors. Experimental evaluation demonstrates superior performance compared
with traditional machine learning models.
| Item Type: | Article |
|---|---|
| Domains: | Computer Applications Education |
| Depositing User: | User 10 |
| Date Deposited: | 08 Sep 2026 17:24 |
| Last Modified: | 08 Sep 2026 17:24 |
| URI: | https://ir.vistas.ac.in/id/eprint/22954 |
Actions (login required)
- View Item