Title: A context-enriched dataset for recommender systems

Authors: Rim Dridi

Addresses: LIPSIC Laboratory, Faculty of Sciences of Tunis, University of Tunis El Manar, Tunis, 2092, Tunisia

Abstract: Recommender systems play a key role in modern applications. Recognising the importance of user context, researchers have developed context-aware recommender systems (CARS) to generate more personalised and relevant recommendations. Even though there are several approaches working for this kind of recommendation, suitable and publicly available datasets including user's contextual ratings are limited, and generally, even these are not large enough to assess CARS properly. To mitigate the contextual datasets availability problem, we propose an enrichment methodology to generate large datasets to be used for context-aware recommender systems evaluation. Our work aims to enrich existing large recommendation datasets by including contextual information to describe users expressed preferences linked to their corresponding contexts. Our assessment with the generated large contextual datasets has revealed promising findings when compared to publicly available contextual datasets.

Keywords: recommender system; context; dataset; enrichment.

DOI: 10.1504/IJIIDS.2026.155294

International Journal of Intelligent Information and Database Systems, 2026 Vol.18 No.3/4, pp.456 - 481

Received: 18 Dec 2023
Accepted: 30 Oct 2024
Published online: 30 Jul 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article