RecKG-Web: A web-based interactive visualization tool for standardized knowledge graphs in recommender systems
Knowledge graphs (KG) enhance recommender systems (RS) by addressing challenges like the long-tail and cold-start problems through rich semantic relationships. However, inconsistent metadata across RS datasets limits interoperability. To solve this, we present RecKG-Web, a user-friendly application that standardizes and integrates heterogeneous datasets using the RecKG format. It supports data upload, mapping, graph-based visualization, and dataset export, enabling cross-domain recommendations and improving accessibility for researchers and practitioners. RecKG-Web bridges the gap between KG theory and practice, advancing KG-aware RS development.
Authors
- Myung Seok Jeon
- Euijong Lee (ORCID: https://orcid.org/0000-0002-7308-7392)
- Young-Duk Seo (ORCID: https://orcid.org/0000-0001-8542-2058)
- Junhyung Park (ORCID: https://orcid.org/0000-0002-0805-6362)
Institutions
- Chungbuk National University (KR)
- Inha University (KR)
Publication Details
- Journal
- SoftwareX
- Published
- 2025-08-28
- DOI
- https://doi.org/10.1016/j.softx.2025.102319
- Primary Topic
- Recommender Systems and Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Inha University
- Ministry of Science and ICT, South Korea
- Institute for Information and Communications Technology Promotion