An Adaptive Cross-Domain Recommendation Framework for Structurally Disjoint Domains via Semantic Representation and Similar-User Knowledge Transfer

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

This study addresses cross-domain recommendation when source-domain users and target-domain items are structurally disjoint. We propose an adaptive framework that embeds source behavior and target-item information in a shared semantic space. Its shared core combines semantic similarity, keyword mapping, preference compatibility, similar-user retrieval, and behavior transfer, while a domain-aware adaptive layer activates scenario-specific signals only when the user supplies the corresponding preference. Post-ranking explanations are generated by a separate language model. The framework was evaluated in hobby-to-volunteer and consumption-to-travel scenarios using human and LLM-based relevance judgments and eight baselines, including content-based hybrids with and without transfer and a direct LLM ranker. In Case A, the revised cold-start score outperformed the earlier content hybrid with transfer (Precision@10: 0.420 vs. 0.258; Holm-adjusted p < 0.001; Cohen’s dz = 0.90) but did not differ significantly from semantic similarity alone. The transfer term did not yield a statistically detectable incremental ranking gain in either scenario. In Case B, a two-by-two factorial analysis identified the adaptive layer as the main source of improvement (+0.363 Precision@10; p < 0.001; dz = 1.04), while a control without the adaptive layer showed that part of the association between active signals and performance reflected profile specificity. An exploratory Case A control found no significant explanation-associated change in automated scores. Human–LLM agreement was positive but limited, supporting automated evaluation as a scalable complement rather than a replacement for human judgment.