{"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/attentive-long-short-term-preference-modeling","title":"Attentive Long Short-Term Preference Modeling for Personalized Product Search","arxiv_id":"1811.10155","date":"2018-11-26","proceeding":null,"authors":["Guo Yangyang","Cheng Zhiyong","Nie Liqiang","Wang Yinglong","Ma Jun","Kankanhalli Mohan"],"abstract":"E-commerce users may expect different products even for the same query, due\nto their diverse personal preferences. It is well-known that there are two\ntypes of preferences: long-term ones and short-term ones. The former refers to\nuser' inherent purchasing bias and evolves slowly. By contrast, the latter\nreflects users' purchasing inclination in a relatively short period. They both\naffect users' current purchasing intentions. However, few research efforts have\nbeen dedicated to jointly model them for the personalized product search. To\nthis end, we propose a novel Attentive Long Short-Term Preference model, dubbed\nas ALSTP, for personalized product search. Our model adopts the neural networks\napproach to learn and integrate the long- and short-term user preferences with\nthe current query for the personalized product search. In particular, two\nattention networks are designed to distinguish which factors in the short-term\nas well as long-term user preferences are more relevant to the current query.\nThis unique design enables our model to capture users' current search\nintentions more accurately. Our work is the first to apply attention mechanisms\nto integrate both long- and short-term user preferences with the given query\nfor the personalized search. Extensive experiments over four Amazon product\ndatasets show that our model significantly outperforms several state-of-the-art\nproduct search methods in terms of different evaluation metrics.","url_abs":"http://arxiv.org/abs/1811.10155v1","url_pdf":"http://arxiv.org/pdf/1811.10155v1.pdf","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":"attentive-long-short-term-preference-modeling","repo_url":"https://github.com/guoyang9/ALSTP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}