{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T02:38:09Z","timestamp":1755225489463,"version":"3.43.0"},"reference-count":40,"publisher":"Emerald","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,15]]},"abstract":"<jats:sec>\n                  <jats:title>Purpose<\/jats:title>\n                  <jats:p>Reviews, serving as authentic user feedback, encompass rich semantic information, including descriptions of user preferences and item characteristics. Introducing reviews as auxiliary information into recommendation systems can enhance the modeling of user and item feature representations. However, existing methods insufficiently account for the semantic variations of review words across different contextual scales, often leading to suboptimal representations of review information. In addition, they fail to effectively integrate review features with interaction features, resulting in a semantic gap between the two modalities. To address these issues, this paper aims to propose a novel review-based recommendation model that incorporates a multi-scale context-aware network and a cross-attention mechanism (MSCA).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Design\/methodology\/approach<\/jats:title>\n                  <jats:p>MSCA uses a multi-scale convolutional network to capture the semantic representations of words in reviews across different contextual scales. It then uses a self-attention layer to learn the associations among reviews, enhancing the representation of review features. Subsequently, MSCA deploys a cross-attention mechanism to emulate personalized attention across different users and items, effectively fusing interaction features with the semantic features of reviews.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Findings<\/jats:title>\n                  <jats:p>Experiments on five Amazon review data sets demonstrate that the proposed model outperforms baseline methods in terms of evaluation metrics.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Originality\/value<\/jats:title>\n                  <jats:p>The authors propose MSCA, a novel recommendation model that more effectively extracts review features using a multi-scale context-aware network. It also uses a cross-attention mechanism to fuse semantic information with interaction features from two modalities, thereby improving the performance of recommendation systems.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1108\/ijwis-10-2024-0311","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T07:26:39Z","timestamp":1745825199000},"page":"205-229","source":"Crossref","is-referenced-by-count":0,"title":["MSCA: a multi-scale context-aware recommender system leveraging reviews and user interactions"],"prefix":"10.1108","volume":"21","author":[{"given":"Zhangyu","family":"Jin","sequence":"first","affiliation":[{"name":"School of Computer Science , Wuhan University, Wuhan,","place":["China"]}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science , Wuhan University, Wuhan,","place":["China"]}]},{"given":"Duantengchuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science , Wuhan University, Wuhan,","place":["China"]}]},{"given":"Maodong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science , Wuhan University, Wuhan,","place":["China"]}]},{"given":"Bingng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science , Wuhan University, Wuhan,","place":["China"]}]}],"member":"140","published-online":{"date-parts":[[2025,4,30]]},"reference":[{"key":"2025081308472070300_ref001","first-page":"28","article-title":"TOPICMF: simultaneously exploiting ratings and reviews for recommendation","author":"Bao","year":"2014"},{"key":"2025081308472070300_ref002","first-page":"288","article-title":"TRANSNETS: learning to transform for recommendation","author":"Catherine","year":"2017"},{"key":"2025081308472070300_ref003","first-page":"357","article-title":"CROSSVIT: cross-attention multi-scale vision transformer for image classification","author":"Chen","year":"2021"},{"key":"2025081308472070300_ref004","first-page":"1583","article-title":"Neural attentional rating regression with review-level explanations","author":"Chen","year":"2018"},{"key":"2025081308472070300_ref005","first-page":"147","article-title":"ANR: aspect-based neural recommender","author":"Chin","year":"2018"},{"key":"2025081308472070300_ref006","first-page":"355","article-title":"Neural factorization machines for sparse predictive analytics","author":"He","year":"2017"},{"key":"2025081308472070300_ref007","first-page":"507","article-title":"Ups and downs: modeling the visual evolution of fashion trends with one-class collaborative filtering","author":"He","year":"2016"},{"key":"2025081308472070300_ref008","first-page":"1746","article-title":"Convolutional neural networks for sentence classification","author":"Kim","year":"2014"},{"key":"2025081308472070300_ref009","first-page":"320","article-title":"Cross-attention transformer for video interpolation","author":"Kim","year":"2022"},{"key":"2025081308472070300_ref010","first-page":"426","article-title":"Factorization meets the neighborhood: a multifaceted collaborative filtering model","author":"Koren","year":"2008"},{"key":"2025081308472070300_ref011","doi-asserted-by":"crossref","first-page":"120438","DOI":"10.1016\/j.ins.2024.120438","article-title":"Multi-perspective knowledge graph completion with global and interaction features","volume":"666","author":"Li","year":"2024","journal-title":"Information Sciences"},{"issue":"4","key":"2025081308472070300_ref012","doi-asserted-by":"crossref","first-page":"103348","DOI":"10.1016\/j.ipm.2023.103348","article-title":"Knowledge graph representation learning with simplifying hierarchical feature propagation","volume":"60","author":"Li","year":"2023","journal-title":"Information Processing and Management"},{"issue":"3","key":"2025081308472070300_ref013","doi-asserted-by":"crossref","first-page":"103631","DOI":"10.1016\/j.ipm.2023.103631","article-title":"Joint inter-word and inter-sentence multi-relation modeling for summary-based recommender system","volume":"61","author":"Li","year":"2024","journal-title":"Information Processing and Management"},{"key":"2025081308472070300_ref014","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/j.neucom.2021.03.122","article-title":"CARM: confidence-aware recommender model via review representation learning and historical rating behavior in the online platforms","volume":"455","author":"Li","year":"2021","journal-title":"Neurocomputing"},{"key":"2025081308472070300_ref015","doi-asserted-by":"crossref","first-page":"111253","DOI":"10.1016\/j.knosys.2023.111253","article-title":"SDFORMER: a shallow-to-deep feature interaction for knowledge graph embedding","volume":"284","author":"Li","year":"2024","journal-title":"Knowledge-Based Systems"},{"issue":"3","key":"2025081308472070300_ref016","doi-asserted-by":"crossref","first-page":"3859","DOI":"10.1109\/TNNLS.2022.3200480","article-title":"A hierarchical attention network for cross-domain group recommendation","volume":"35","author":"Liang","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2025081308472070300_ref017","first-page":"105","article-title":"Ratings meet reviews, a combined approach to recommend","author":"Ling","year":"2014"},{"key":"2025081308472070300_ref018","first-page":"344","article-title":"DAML: dual attention mutual learning between ratings and reviews for item recommendation","author":"Liu","year":"2019"},{"issue":"3","key":"2025081308472070300_ref019","doi-asserted-by":"crossref","first-page":"103680","DOI":"10.1016\/j.ipm.2024.103680","article-title":"Integrating user -term intentions and long-term preferences in heterogeneous hypergraph networks for sequential recommendation","volume":"61","author":"Liu","year":"2024","journal-title":"Information Processing and Management"},{"issue":"5","key":"2025081308472070300_ref020","doi-asserted-by":"crossref","first-page":"2076","DOI":"10.1109\/TKDE.2020.3010949","article-title":"Adaptive hierarchical attention-enhanced gated network integrating reviews for item recommendation","volume":"34","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2025081308472070300_ref021","first-page":"658","article-title":"Learning hierarchical review graph representations for recommendation","volume":"35","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2025081308472070300_ref022","first-page":"1566","article-title":"SMEF: social-aware multi-dimensional edge features-based graph representation learning for recommendation","author":"Liu","year":"2023"},{"key":"2025081308472070300_ref023","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.neucom.2021.10.050","article-title":"Multi-perspective social recommendation method with graph representation learning","volume":"468","author":"Liu","year":"2022","journal-title":"Neurocomputing"},{"key":"2025081308472070300_ref024","first-page":"475","article-title":"Disentangled hypergraph collaborative filtering for social recommendation","author":"Liu","year":"2023"},{"issue":"7","key":"2025081308472070300_ref025","doi-asserted-by":"crossref","first-page":"4361","DOI":"10.1109\/TII.2021.3128240","article-title":"EDMF: efficient deep matrix factorization with review feature learning for industrial recommender system","volume":"18","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Industrial Informatics"},{"article-title":"Hierarchical question-image co-attention for visual question answering, in: Advances in neural information processing systems","year":"2016","author":"Lu","key":"2025081308472070300_ref026"},{"key":"2025081308472070300_ref027","first-page":"165","article-title":"Hidden factors and hidden topics: understanding rating dimensions with review text","author":"McAuley","year":"2013"},{"key":"2025081308472070300_ref028","first-page":"43","article-title":"Image-based recommendations on styles and substitutes","author":"McAuley","year":"2015"},{"key":"2025081308472070300_ref029","article-title":"Probabilistic matrix factorization","author":"Mnih","year":"2007","journal-title":"in: Advances in Neural Information Processing Systems"},{"key":"2025081308472070300_ref030","doi-asserted-by":"crossref","first-page":"995","DOI":"10.1109\/ICDM.2010.127","article-title":"Factorization machines","volume-title":"2010 IEEE International Conference on Data Mining","author":"Rendle","year":"2010"},{"key":"2025081308472070300_ref031","first-page":"297","article-title":"Interpretable convolutional neural networks with dual local and global attention for review rating prediction","author":"Seo","year":"2017"},{"key":"2025081308472070300_ref032","first-page":"1283","article-title":"A review-aware graph contrastive learning framework for recommendation","author":"Shuai","year":"2022"},{"key":"2025081308472070300_ref033","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"2025081308472070300_ref034","first-page":"535","article-title":"Knowledge-adaptive contrastive learning for recommendation","author":"Wang","year":"2023"},{"issue":"4","key":"2025081308472070300_ref035","doi-asserted-by":"crossref","first-page":"103350","DOI":"10.1016\/j.ipm.2023.103350","article-title":"Knowledge graph embedding model with attention-based high-low level features interaction convolutional network","volume":"60","author":"Wang","year":"2023","journal-title":"Information Processing and Management"},{"issue":"17","key":"2025081308472070300_ref036","doi-asserted-by":"crossref","first-page":"16386","DOI":"10.1109\/JIOT.2022.3151400","article-title":"EAGCN: an efficient adaptive graph convolutional network for item recommendation in social internet of things","volume":"9","author":"Wu","year":"2022","journal-title":"IEEE Internet of Things Journal"},{"issue":"7","key":"2025081308472070300_ref037","doi-asserted-by":"crossref","first-page":"4039","DOI":"10.1109\/TSMC.2023.3242308","article-title":"Graph-augmented co-attention model for socio-sequential recommendation","volume":"53","author":"Wu","year":"2023","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"2025081308472070300_ref038","first-page":"4884","article-title":"Reviews meet graphs: enhancing user and item representations for recommendation with hierarchical attentive graph neural network","author":"Wu","year":"2019"},{"key":"2025081308472070300_ref039","first-page":"3119","article-title":"Attentional factorization machines: learning the weight of feature interactions via attention networks","author":"Xiao","year":"2017"},{"key":"2025081308472070300_ref040","first-page":"425","article-title":"Joint deep modeling of users and items using reviews for recommendation","author":"Zheng","year":"2017"}],"container-title":["International Journal of Web Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJWIS-10-2024-0311\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/ijwis\/article-pdf\/21\/3\/205\/10063606\/ijwis-10-2024-0311.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ijwis\/article-pdf\/21\/3\/205\/10063606\/ijwis-10-2024-0311.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T12:47:31Z","timestamp":1755089251000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ijwis\/article\/21\/3\/205\/1273628\/MSCA-a-multi-scale-context-aware-recommender"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,30]]},"references-count":40,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,5,15]]}},"URL":"https:\/\/doi.org\/10.1108\/ijwis-10-2024-0311","relation":{},"ISSN":["1744-0084","1744-0092"],"issn-type":[{"type":"print","value":"1744-0084"},{"type":"electronic","value":"1744-0092"}],"subject":[],"published":{"date-parts":[[2025,4,30]]}}}