Hybrid Approach to Recommender System Model

DOI

10.2991/978-94-6463-716-8_28How to use a DOI?

Keywords

Recommender Systems; Hybrid Recommender System; Collaborative Filtering

Abstract

Recommender systems are a popular research area broadly applied, from e-commerce to e-learning systems. The paper presents a hybrid approach to recommender systems that leverages user reviews, clustering, and sentiment analysis to enhance recommendation accuracy. Traditional models primarily rely on user ratings, often neglecting the rich contextual information in textual reviews. The proposed method extracts user preferences by analyzing review content through sentiment analysis and clustering techniques, providing a more nuanced understanding of user tastes and preferences. By incorporating this detailed preference data and contextual information, the system generates Top-N recommendations that are relevant to the user and personalized. We applied our model to the Yelp dataset, which includes diverse and extensive user reviews of various businesses. Comparative evaluations demonstrate that our approach significantly outperforms traditional models based solely on user ratings, achieving higher accuracy in recommendation predictions. The results underscore the importance of utilizing multidimensional data sources in recommendation systems, highlighting the potential for improved user satisfaction and engagement. This study contributes to recommender systems by showcasing the benefits of a comprehensive analysis of user-generated content and its impact on recommendation quality.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Abhilasha Sankari
AU  - Shraddha Masih
AU  - Maya Ingle
PY  - 2025
DA  - 2025/05/26
TI  - Hybrid Approach to Recommender System Model
BT  - Proceedings of the International Conference on Recent Advancements and Modernisations in Sustainable Intelligent Technologies and Applications (RAMSITA 2025)
PB  - Atlantis Press
SP  - 349
EP  - 360
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-716-8_28
DO  - 10.2991/978-94-6463-716-8_28
ID  - Sankari2025
ER  -