Kotevski, Aleksandar and Ristevski, Blagoj (2025) Improving Learning Recommendations Through Combined Audio and Text-based Sentiment Insights. In: 15th International Conference on Applied Internet and Information Technologies (AIIT 2025), 7.11.2015, Bitola, Republic of Macedonia.
![[thumbnail of AIIT 2025_AK_BR.pdf]](https://eprints.uklo.edu.mk/style/images/fileicons/text.png) |
Text
AIIT 2025_AK_BR.pdf - Published Version Download (1MB) |
Abstract
This research proposes an adaptive learning material recommender system that employs sentiment analysis to enhance personalization and effectiveness in online learning. The system dynamically adapts to a learner’s emotional state and engagement levels by incorporating
explicit feedback (ratings, comments, reviews) and implicit feedback (interaction patterns, time spent, dropout behavior). At its core, the proposed system integrates collaborative filtering, content-based methods, and sentiment analysis. Learners and learning materials are
represented as dense vector embedding, while sentiment analysis is applied to both textual feedback and behavioral signals to capture emotional state and motivation. Models from Hugging Face’s sentence-transformers library generate semantic embedding of feedback and material descriptions. Similarity is measured using cosine similarity or Euclidean distance, allowing recommendations to reflect not only contextual relevance but also the learner’s affective state. Our experimental evaluation, conducted on real-world datasets, demonstrates that sentiment-aware adaptation significantly improves learning outcomes. The dataset-rich
user comments and feedback enabled testing of the proposed pipeline. The framework offers a scalable, data-driven approach for delivering emotionally responsive and personalized learning experiences, addressing the growing demand for human-centered technologies in online education.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Subjects: | Scientific Fields (Frascati) > Natural sciences > Computer and information sciences Scientific Fields (Frascati) > Engineering and Technology > Electrical engineering, electronic engineering,information engineering |
| Divisions: | Faculty of Information and Communication Technologies |
| Depositing User: | Prof. d-r. Blagoj Ristevski |
| Date Deposited: | 10 Dec 2025 10:21 |
| Last Modified: | 10 Dec 2025 10:21 |
| URI: | https://eprints.uklo.edu.mk/id/eprint/11265 |
Actions (login required)
 |
View Item |