Social Knowledge for Cross-Domain User Preference Modeling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917331187269632 |
|---|---|
| author | Lotan, Nir Solomon, Adir Guy, Ido Minkov, Einat |
| author_facet | Lotan, Nir Solomon, Adir Guy, Ido Minkov, Einat |
| contents | We demonstrate that user preferences can be represented and predicted across topical domains using large-scale social modeling. Given information about popular entities favored by a user, we project the user into a social embedding space learned from a large-scale sample of the Twitter (now X) network. By representing both users and popular entities in a joint social space, we can assess the relevance of candidate entities (e.g., music artists) using cosine similarity within this embedding space. A comprehensive evaluation using link prediction experiments shows that this method achieves effective personalization in zero-shot setting, when no user feedback is available for entities in the target domain, yielding substantial improvements over a strong popularity-based baseline. In-depth analysis further illustrates that socio-demographic factors encoded in the social embeddings are correlated with user preferences across domains. Finally, we argue and demonstrate that the proposed approach can facilitate social modeling of end users using large language models (LLMs). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10148 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Social Knowledge for Cross-Domain User Preference Modeling Lotan, Nir Solomon, Adir Guy, Ido Minkov, Einat Social and Information Networks Artificial Intelligence We demonstrate that user preferences can be represented and predicted across topical domains using large-scale social modeling. Given information about popular entities favored by a user, we project the user into a social embedding space learned from a large-scale sample of the Twitter (now X) network. By representing both users and popular entities in a joint social space, we can assess the relevance of candidate entities (e.g., music artists) using cosine similarity within this embedding space. A comprehensive evaluation using link prediction experiments shows that this method achieves effective personalization in zero-shot setting, when no user feedback is available for entities in the target domain, yielding substantial improvements over a strong popularity-based baseline. In-depth analysis further illustrates that socio-demographic factors encoded in the social embeddings are correlated with user preferences across domains. Finally, we argue and demonstrate that the proposed approach can facilitate social modeling of end users using large language models (LLMs). |
| title | Social Knowledge for Cross-Domain User Preference Modeling |
| topic | Social and Information Networks Artificial Intelligence |
| url | https://arxiv.org/abs/2603.10148 |