Dynamic Communities: A Novel Recommendation Approach for Individuals and Groups

Sabrine Ben Abdrabbah, Sabrine Mallek () and Nahla Ben Amor
Additional contact information
Sabrine Mallek: ICN Business School, CEREFIGE - Centre Européen de Recherche en Economie Financière et Gestion des Entreprises - UL - Université de Lorraine
Nahla Ben Amor: LARODEC - Laboratoire de Recherche Opérationnelle de Décision et de Contrôle de Processus - Université de Tunis - ISG de Tunis

Post-Print from HAL

Abstract: As user preferences rapidly and continually evolve, it becomes crucial to incorporate these temporal dynamics in the design of recommender systems. This paper proposes a novel dynamic and overlapping community-based recommender system framework, which considers the evolving nature of users' preferences to suggest items distinctly for both individuals and groups. Using temporal networks to capture the dynamic interplay of users' interests, we apply dynamic community detection techniques to identify similar items, thereby addressing scalability issues. To cater to group recommendation scenarios, the framework leverages users' satisfaction with similar items, thereby mitigating data sparsity and delivering a broad range of recommendations. Experimental results show that the proposed system outperforms state-of-the-art approaches in terms of recommendation accuracy for both individual and group recommendations.

Keywords: Recommendation systems; Group Recommendation; Dynamic community detection; Overlapping communities; Dynamic networks (search for similar items in EconPapers)
Date: 2024-03-15
References: Add references at CitEc
Citations:

Published in Agents and Artificial Intelligence, 14546, Springer Nature Switzerland, pp.187-201, 2024, Lecture Notes in Computer Science, ⟨10.1007/978-3-031-55326-4_9⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-04550011

DOI: 10.1007/978-3-031-55326-4_9

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().