{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unifying-paragraph-embeddings-and-neural","title":"Unifying paragraph embeddings and neural collaborative filtering for hybrid recommendation","arxiv_id":null,"date":"2020-01-20","proceeding":"03/16 2020 1","authors":["Yihao Zhang a","Zhi Liu a","∗","Chunyan Sang b"],"abstract":"Collaborative filtering is one of widely used recommendation techniques. Despite the effectiveness\r\nof matrix factorization for collaborative filtering; however, the inner product operator, combining the\r\nmultiplication of latent features linearly, may not be sufficient to capture the complex structure of user\r\ninteraction ratings. On the other hand, we argue that there is a great deviation between user ratings\r\nand their real interest preference. In this paper, we propose a novel hybrid recommendation algorithm.\r\nIt adopts neural networks to exploit user–item ratings for collaborative filtering, which is endowed a\r\nhigh level of non-linearity for capturing the complex structure of user interaction ratings. At the same\r\ntime, it exploits item embeddings to capture the content feature for auxiliary information, which solves\r\nthe cold start problem to some extent. In particular, we introduce paragraph embeddings to represent\r\nuser reviews and item descriptions, and design two neural networks to capture the sentiment of\r\nuser reviews and the content feature of items, respectively. And then, we treat these embeddings\r\nas attention weights of users and items, and unify them with user–item ratings to model the hybrid\r\nrecommendation system. Extensive experiments on Amazon product dataset demonstrates that our\r\nalgorithm performs better on rating prediction than other state-of-the-art algorithms","url_abs":"https://www.sciencedirect.com/science/article/abs/pii/S1568494621002684","url_pdf":"https://www.researchgate.net/publication/350438263_Unifying_paragraph_embeddings_and_neural_collaborative_filtering_for_hybrid_recommendation","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"unifying-paragraph-embeddings-and-neural","repo_url":"https://github.com/MAHMOUDRR707/paragraph-embeddings-and-neural-collaborative-filtering-for-hybrid-recommendation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"collaborative-filtering","task_name":"Collaborative Filtering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}