Enhancement of Content-Based Recommender Systems using Particle Swarm Optimization to Reduce Over-Specialization
Preprint
- 18 June 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Content-Based Recommender Systems (CBRS) are widely used owing to their independence from extensive interaction histories. However, they often suffer from over-specialization, producing overly homogeneous recommendations that hinder user discovery. Existing enhancements, including TF-IDF modeling, ONMTF-based similarity extraction, and evolutionary techniques such as genetic algorithms, have partially improved novelty or diversity but have not jointly balanced relevance, novelty, diversity, and unexpectedness to induce serendipity. To address this gap, this study proposes ImprovedCBRS-PSO, a Particle Swarm Optimization (PSO) enhanced re-ranking framework designed to inject serendipity while preserving its relevance. The model integrates a discreet PSO formulation, roulette-wheel-based exploratory search, and a multi-criteria fitness function that combines precision, relevance, novelty, diversity, and serendipity. Experiments on MovieLens-1M, MovieLens-10M, and AmazonBooks demonstrated that the proposed method consistently outperformed CBRS+RRSGA (Revolutionary Recommender System using a Genetic Algorithm) and CBRS+EEDPSO (Elite-Evolutionary Discrete Particle Swarm Optimization), achieving up to 92% gains in Serendipity while maintaining a strong precision. Superior performance on the sparse AmazonBooks dataset further validates the effectiveness of PSO in navigating long-tail environments. Moreover, stable results across K = 1–10 indicating a robust balance between exploration and relevance in the results. Overall, the findings confirm PSO as an effective exploratory mechanism for mitigating over-specialization in the CBRS.Keywords
This publication has 20 references indexed in Scilit:
- Serendipity in the city: User evaluations of urban recommender systemsJournal of the Association for Information Science and Technology, 2021
- Serendipity in Recommender Systems: A Systematic Literature ReviewJournal of Computer Science and Technology, 2021
- Content‐Based Recommender Systems2020
- Assessing ranking metrics in top-N recommendationInformation Retrieval Journal, 2020
- Swarm intelligence techniques in recommender systems - A review of recent researchSwarm and Evolutionary Computation, 2019
- Diversity in recommender systems – A surveyKnowledge-Based Systems, 2017
- An investigation on the serendipity problem in recommender systemsInformation Processing & Management, 2015
- Particle swarm optimization2014
- Content-based Recommender Systems: State of the Art and Trends2010
- Discrete Particle Swarm Optimization, illustrated by the Traveling Salesman Problem2004