Aspect-grounded heterogeneous graph learning for explainable cross-domain recommendation
Personalized recommender systems are essential for mitigating information overload. However, existing approaches face challenges in fine-grained preference modeling, behaviorally relevant explanations, and cross-domain transfer. We propose Aspect-Grounded Heterogeneous Graph Learning (AGHGL), a recommendation framework that uses aspect-level sentiment semantics as a common basis for preference modeling, explanation, and cross-domain transfer. AGHGL constructs a heterogeneous sentiment graph integrating users, items, aspects, and opinion expressions, enabling relation-aware message passing and aspect-mediated preference modeling. A margin-based intervention-sensitivity objective couples attention-derived aspect importance with prediction changes under aspect masking, aligning explanations with prediction behavior. A dual-level aspect alignment mechanism facilitates cross-domain transfer by aligning aspect representations at semantic and graph-structural levels. Experiments on real-world datasets show that AGHGL consistently outperforms the evaluated baselines in recommendation accuracy, with larger relative gains under sparse and cold-start conditions in the target domain. Human evaluation indicates improved perceived explanatory quality, while intervention-based analysis shows that higher aspect importance is associated with larger prediction changes. These results suggest that the aspect-grounded framework provides a useful basis for jointly modeling recommendation, explanation, and cross-domain transfer within the evaluated settings.
Authors
- Ah-Lian Kor (ORCID: https://orcid.org/0000-0001-9514-3773)
- Kok Weng Ng (ORCID: https://orcid.org/0000-0001-6910-0040)
- Jianbang Liu (ORCID: https://orcid.org/0009-0003-2937-5498)
- Zhaosheng Xu (ORCID: https://orcid.org/0000-0002-8952-6505)
- Mei Choo Ang (ORCID: https://orcid.org/0000-0001-5316-3936)
- Xiaowei Liu
Institutions
- University of Nottingham (GB)
- University of Nottingham Malaysia Campus (MY)
- Xinyu University (CN)
- Leeds Beckett University (GB)
- National University of Malaysia (MY)
Publication Details
- Journal
- Scientific Reports
- Published
- 2026-11-16
- DOI
- https://doi.org/10.1038/s41598-026-79433-x
- Primary Topic
- Recommender Systems and Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00