{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T17:14:11Z","timestamp":1769361251589,"version":"3.49.0"},"reference-count":37,"publisher":"Emerald","issue":"2","license":[{"start":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T00:00:00Z","timestamp":1621209600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["EL"],"published-print":{"date-parts":[[2021,7,17]]},"abstract":"Purpose<\/jats:title>Aspects extracted from the user\u2019s historical records are widely used to define user\u2019s fine-grained preferences for building interpretable recommendation systems. As the aspects were extracted from the historical records, the aspects that represent user\u2019s negative preferences cannot be identified because of their absence from the records. However, these latent aspects are also as important as those aspects representing user\u2019s positive preferences for building a recommendation system. This paper aims to identify the user\u2019s positive preferences and negative preferences for building an interpretable recommendation.<\/jats:p><\/jats:sec>Design\/methodology\/approach<\/jats:title>First, high-frequency tags are selected as aspects to describe user preferences in aspect-level. Second, user positive and negative preferences are calculated according to the positive and negative preference model, and the interaction between similar aspects is adopted to address the aspect sparsity problem. Finally, an experiment is designed to evaluate the effectiveness of the model. The code and the experiment data link is:https:\/\/github.com\/shiyu108\/Recommendation-system<\/jats:ext-link><\/jats:p><\/jats:sec>Findings<\/jats:title>Experimental results show the proposed approach outperformed the state-of-the-art methods in widely used public data sets. These latent aspects are also as important as those aspects representing the user\u2019s positive preferences for building a recommendation system.<\/jats:p><\/jats:sec>Originality\/value<\/jats:title>This paper provides a new approach that identifies and uses not only users\u2019 positive preferences but also negative preferences, which can capture user preference precisely. Besides, the proposed model provides good interpretability.<\/jats:p><\/jats:sec>","DOI":"10.1108\/el-06-2020-0154","type":"journal-article","created":{"date-parts":[[2021,5,14]],"date-time":"2021-05-14T02:53:06Z","timestamp":1620960786000},"page":"281-295","source":"Crossref","is-referenced-by-count":4,"title":["Using latent features for building an interpretable recommendation system"],"prefix":"10.1108","volume":"39","author":[{"given":"Ziming","family":"Zeng","sequence":"first","affiliation":[]},{"given":"Yu","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Lavinia Florentina","family":"Pieptea","sequence":"additional","affiliation":[]},{"given":"Junhua","family":"Ding","sequence":"additional","affiliation":[]}],"member":"140","published-online":{"date-parts":[[2021,5,17]]},"reference":[{"key":"key2021072116263075200_ref001","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1007\/978-1-4899-7637-6_25","article-title":"Multi-criteria recommender systems","volume-title":"Recommender Systems Handbook","year":"2015"},{"issue":"6","key":"key2021072116263075200_ref002","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1109\/TKDE.2005.99","article-title":"Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions","volume":"17","year":"2005","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"key2021072116263075200_ref003","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1145\/3097983.3098170","article-title":"Aspect based recommendations: Recommending items with the most valuable aspects based on user reviews","volume-title":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","year":"2017"},{"key":"key2021072116263075200_ref004","first-page":"51","article-title":"Discriminative reordering with Chinese grammatical relations features","volume-title":"Proceedings of the Third Workshop on Syntax and Structure in Statistical Translation (SSST-3) at NAACL HLT \u201809","year":"2009"},{"key":"key2021072116263075200_ref005","first-page":"1681","article-title":"JIT2R: a joint framework for item tagging and tag-based recommendation","volume-title":"The 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR \u201820)","year":"2020"},{"issue":"2","key":"key2021072116263075200_ref006","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3291060","article-title":"MMALFM: Explainable recommendation by leveraging reviews and images","volume":"37","year":"2019","journal-title":"ACM Transactions on Information Systems"},{"key":"key2021072116263075200_ref007","first-page":"639","article-title":"Aspect-aware latent factor model: rating prediction with ratings and reviews","volume-title":"Proceedings of the 2018 World Wide Web Conference","year":"2018"},{"key":"key2021072116263075200_ref008","first-page":"3748","article-title":"A^ 3NCF: an adaptive aspect attention model for rating prediction","volume-title":"International Joint Conference on Artificial Intelligence","year":"2018"},{"key":"key2021072116263075200_ref009","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1145\/2911451.2911549","article-title":"Learning to rank features for recommendation over multiple categories","volume-title":"Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval","year":"2016"},{"key":"key2021072116263075200_ref010","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1145\/3025171.3025173","article-title":"Explaining recommendations based on feature sentiments in product reviews","volume-title":"Proceedings of the 22nd International Conference on Intelligent User Interfaces","year":"2017"},{"key":"key2021072116263075200_ref011","first-page":"1","article-title":"Objective evaluation or subjective evaluation in digital social media: a further understanding of online user\u2019s rating of movies","volume-title":"Proceedings of the 1st International Conference on Digital Tools and Uses Congress","year":"2018"},{"issue":"2","key":"key2021072116263075200_ref012","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1177\/0165551506062337","article-title":"Usage patterns of collaborative tagging systems","volume":"32","year":"2006","journal-title":"Journal of Information Science"},{"issue":"3","key":"key2021072116263075200_ref013","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3309546","article-title":"Attentive aspect modeling for review-aware recommendation","volume":"37","year":"2019","journal-title":"ACM Transactions on Information Systems"},{"key":"key2021072116263075200_ref014","doi-asserted-by":"crossref","first-page":"1661","DOI":"10.1145\/2806416.2806504","article-title":"TriRank: review-aware explainable recommendation by modeling aspects","volume-title":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","year":"2015"},{"key":"key2021072116263075200_ref015","first-page":"173","article-title":"Neural collaborative filtering","volume-title":"Proceedings of the 26th International Conference on the World Wide Web","year":"2017"},{"key":"key2021072116263075200_ref016","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1145\/1014052.1014073","article-title":"Mining and summarizing customer reviews","volume-title":"Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","year":"2004"},{"issue":"3","key":"key2021072116263075200_ref017","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1002\/asi.10372","article-title":"A graph model for e\u2010commerce recommender systems","volume":"55","year":"2004","journal-title":"Journal of the American Society for Information Science and Technology"},{"issue":"8","key":"key2021072116263075200_ref018","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/MC.2009.263","article-title":"Matrix factorization techniques for recommender systems","volume":"42","year":"2009","journal-title":"Computer"},{"key":"key2021072116263075200_ref019","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3109859.3109915","article-title":"User preferences for hybrid explanations","volume-title":"Proceedings of the Eleventh ACM Conference on Recommender Systems","year":"2017"},{"key":"key2021072116263075200_ref020","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1145\/2124295.2124317","article-title":"Multi-relational matrix factorization using Bayesian personalized ranking for social network data","volume-title":"Proceedings of the Fifth ACM International Conference on Web Search and Data Mining","year":"2012"},{"issue":"1","key":"key2021072116263075200_ref021","first-page":"311","article-title":"Personalized recommendation by matrix co-factorization with tags and time information","volume":"119","year":"2019","journal-title":"Expert Systems with Applications"},{"key":"key2021072116263075200_ref022","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1145\/2507157.2507163","article-title":"Hidden factors and hidden topics: understanding rating dimensions with review text","volume-title":"Proceedings of the 7th ACM Conference on Recommender Systems","year":"2013"},{"key":"key2021072116263075200_ref023","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"key2021072116263075200_ref024","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3243652","article-title":"Transfer to rank for heterogeneous one-class collaborative filtering","volume":"37","year":"2019","journal-title":"ACM Transactions on Information Systems"},{"key":"key2021072116263075200_ref025","first-page":"181","article-title":"Tagging, communities, vocabulary, evolution","volume-title":"Proceedings of the 20th Anniversary Conference on Computer Supported Cooperative Work","year":"2006"},{"key":"key2021072116263075200_ref026","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1145\/3109859.3109890","article-title":"Interpretable convolutional neural networks with dual local and global attention for review rating prediction","volume-title":"Proceedings of the Eleventh ACM Conference on Recommender Systems","year":"2017"},{"key":"key2021072116263075200_ref027","unstructured":"Sinha, R. (2005), \u201cA cognitive analysis of tagging\u201d, available at: http:\/\/rashmisinha.com\/2005\/09\/27\/a-cognitive-analysis-of-tagging\/ (accessed 3 June 2020)."},{"key":"key2021072116263075200_ref028","first-page":"2640","article-title":"Rating-boosted latent topics: understanding users and items with ratings and reviews","volume-title":"International Joint Conference on Artificial Intelligence","year":"2016"},{"key":"key2021072116263075200_ref029","first-page":"5329","article-title":"Explainable reasoning over knowledge graphs for recommendation","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","year":"2019"},{"key":"key2021072116263075200_ref030","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.elerap.2016.01.003","article-title":"A hybrid approach for movie recommendation via tags and ratings","volume":"18","year":"2016","journal-title":"Electronic Commerce Research and Applications"},{"issue":"1","key":"key2021072116263075200_ref031","first-page":"365","article-title":"Contextual-boosted deep neural collaborative filtering model for interpretable recommendation","volume":"136","year":"2019","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"key2021072116263075200_ref034a","first-page":"1","article-title":"Boost phrase-level polarity labelling with review-level sentiment classification","volume":"1","year":"2006","journal-title":"Computational Linguistics"},{"key":"key2021072116263075200_ref032","first-page":"1449","article-title":"Joint representation learning for top-n recommendation with heterogeneous information sources","volume-title":"Proceedings of the 2017 ACM Conference on Information and Knowledge Management","year":"2017"},{"key":"key2021072116263075200_ref033","first-page":"83","article-title":"Explicit factor models for explainable recommendation based on phrase-level sentiment analysis","volume-title":"Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval","year":"2014"},{"key":"key2021072116263075200_ref034","first-page":"1027","article-title":"Do users rate or review? Boost phrase-level sentiment labeling with review-level sentiment classification","volume-title":"Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval","year":"2014"},{"key":"key2021072116263075200_ref035","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1145\/3018661.3018665","article-title":"Joint deep modeling of users and items using reviews for recommendation","volume-title":"Proceedings of the Tenth ACM International Conference on Web Search and Data Mining","year":"2017"},{"issue":"3","key":"key2021072116263075200_ref036","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1016\/j.ipm.2019.02.002","article-title":"Personalized recommendation via user preference matching","volume":"56","year":"2019","journal-title":"Information Processing and Management"}],"container-title":["The Electronic Library"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/EL-06-2020-0154\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/EL-06-2020-0154\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T01:07:27Z","timestamp":1753405647000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/el\/article\/39\/2\/281-295\/83457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,17]]},"references-count":37,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,5,17]]},"published-print":{"date-parts":[[2021,7,17]]}},"alternative-id":["10.1108\/EL-06-2020-0154"],"URL":"https:\/\/doi.org\/10.1108\/el-06-2020-0154","relation":{},"ISSN":["0264-0473","0264-0473"],"issn-type":[{"value":"0264-0473","type":"print"},{"value":"0264-0473","type":"print"}],"subject":[],"published":{"date-parts":[[2021,5,17]]}}}