{"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/knowledge-aware-attentional-neural-network","title":"Knowledge-aware attentional neural network for review-based movie recommendation with explanations","arxiv_id":null,"date":"2022-09-04","proceeding":"Neural Computing and Applications 2022 9","authors":["Yun Liu","Jun Miyazaki"],"abstract":"In this paper, we propose a knowledge-aware attentional neural network (KANN) for dealing with movie recommendation\r\ntasks by extracting knowledge entities from movie reviews and capturing understandable interactions between users and\r\nmovies at the knowledge level. In most recommendation systems, review information is already widely utilized to uncover\r\nthe explicit preferences of users for items, especially for domains including movie recommendations, music recommendations,\r\nand book recommendations, as reviews are full of knowledge entities relevant to the domain. When processing\r\nreview information, current methods usually use word embeddings to represent reviews for modeling users and items. As a\r\nresult, they may split the meaning of a phrase, and thereby induce erroneous predictions. Moreover, most methods capture\r\nhigh-order interactions between users and items after obtaining latent low-dimensional representations, which means they\r\ncannot discover understandable interactions or provide knowledge-level explanations. By incorporating knowledge graph\r\nrepresentation into movie recommendation tasks, the proposed KANN can not only capture the inner attention among user\r\n(movie) reviews but also compute the outer attention values between users and movies before generating corresponding\r\nlatent vector representations. These characteristics enable the explicit preferences of users for movies to be learned and\r\nunderstood. We test our model on two datasets (IMDb and Amazon) for the movie rating prediction task and the clickthrough\r\nrate prediction task and show that it outperforms some of the existing state-of-the-art models and gains outstanding\r\nprediction performances in cases with a very small amount of reviews. Furthermore, we demonstrate the high explainability\r\nof the proposed KANN by visualizing the interaction between users and movies through a case study. Our results\r\nand analyses highlight the relatively high effectiveness and reliability of KANN for movie recommendation tasks.","url_abs":"https://link.springer.com/article/10.1007/s00521-022-07689-1","url_pdf":"https://link.springer.com/content/pdf/10.1007/s00521-022-07689-1.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":"knowledge-aware-attentional-neural-network","repo_url":"https://github.com/liuyuncoder/KANN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"movie-recommendation","task_name":"Movie Recommendation"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}