Enhanced Multimodal Recommendation Systems through Reviews Integration

Enhanced Multimodal Recommendation Systems through Reviews Integration | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Enhanced Multimodal Recommendation Systems through Reviews Integration Hong Fang, Jindong Liang, Leiyuxin Sha This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4333408/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 13 Jan, 2025 Read the published version in Knowledge and Information Systems → Version 1 posted 15 You are reading this latest preprint version Abstract Multimodal recommendation systems aim to capture diverse user preferences through data such as text and images, offering more personalized recommendation services. Accurately grasping user preferences can enhance the precision of recommendations and augment the user experience. Existing models often exploit the external attributes of item to capture users' preferences while neglecting their intrinsic attributes, such as ease of cleaning and cost-effectiveness, which are revealed in reviews. These attributes often reveal themselves in overlooked reviews. However, directly incorporating reviews into the representation will bring additional noise. Therefore, we propose the Personalized Multi-Preference Recommender (PMPR) model, which integrates reviews with multimodal data to extract multifaceted user preferences, enhancing the personalization of recommendations. Specifically, we designed a heterogeneous graph learning module based on reviews and a homogeneous graph learning module that combines the review features with multimodal features to capture users' diverse preferences. Considering the varying informational content of reviews, PMPR processes each review individually and utilizes user IDs to generate review attention vectors for aggregating the review features to reduce review noise. Finally, we integrate the Top-K method for recommendation. We compare common review processing methods with PMPR's approach to validate its effectiveness. In comparative analyses across three publicly available datasets, our enhanced model consistently demonstrated superior performance when benchmarked against seven widely recognized models. The results indicate a noteworthy improvement over the current State-of-the-Art (SOTA) model, ranging from 2.76% to 22.52% in terms of average performance. Multimodal recommendation Multi-Preference graph structure learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 13 Jan, 2025 Read the published version in Knowledge and Information Systems → Version 1 posted Editorial decision: Revision requested 29 Sep, 2024 Reviews received at journal 29 Sep, 2024 Reviews received at journal 05 Sep, 2024 Reviews received at journal 27 Aug, 2024 Reviewers agreed at journal 20 Aug, 2024 Reviewers agreed at journal 19 Aug, 2024 Reviewers agreed at journal 18 Aug, 2024 Reviewers agreed at journal 18 Aug, 2024 Reviewers agreed at journal 18 Aug, 2024 Reviewers agreed at journal 16 Aug, 2024 Reviewers agreed at journal 16 Aug, 2024 Reviewers invited by journal 04 Jun, 2024 Editor assigned by journal 21 May, 2024 Submission checks completed at journal 29 Apr, 2024 First submitted to journal 27 Apr, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4333408","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":308196288,"identity":"763f93b6-4d8c-485c-94a6-dcbb8d298ead","order_by":0,"name":"Hong Fang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYBAC9gYGBmYQgx8qwNhASAvPAagWyQaStRgcIFoL+9nDrwsq7thtPn/82WMeBhvZDQeYnz3Aq4UnL816xplnydtu5Jgb8zCkGW84wGZugE+LPUOOmTFv2+Fksxs8bNI8DIcTNxzgYZPAawv/G4gW4/7jz4Ba/hOhRSLH+DFQi50BQ4IZUMsBYrS8MWPmOXM4QQLoF8M5BsnGMw+zmRFwWI7xZ56Kw/b8QIc9eFNhJ9t3vPkZXi1AAHZGYgOQAYwdBmg04QfMHxhAIQfWMgpGwSgYBaMACwAAta9GKGEYi7gAAAAASUVORK5CYII=","orcid":"","institution":"Shanghai Polytechnic University","correspondingAuthor":true,"prefix":"","firstName":"Hong","middleName":"","lastName":"Fang","suffix":""},{"id":308196289,"identity":"41c45dc4-87ef-48aa-a11e-fb5a2ad4ebf1","order_by":1,"name":"Jindong Liang","email":"","orcid":"","institution":"Shanghai Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Jindong","middleName":"","lastName":"Liang","suffix":""},{"id":308196290,"identity":"77f06c17-fdbe-498f-bdf9-e12f8dcdc3c2","order_by":2,"name":"Leiyuxin Sha","email":"","orcid":"","institution":"Shanghai Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Leiyuxin","middleName":"","lastName":"Sha","suffix":""}],"badges":[],"createdAt":"2024-04-27 09:43:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4333408/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4333408/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10115-024-02309-x","type":"published","date":"2025-01-13T15:57:45+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":74284646,"identity":"c8643c68-de44-4cf5-9c3e-e80bf84ef324","added_by":"auto","created_at":"2025-01-20 16:10:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":680189,"visible":true,"origin":"","legend":"","description":"","filename":"PMPR1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4333408/v1_covered_ceb6516a-f862-4389-bd14-4027c19dbda9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhanced Multimodal Recommendation Systems through Reviews Integration","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"knowledge-and-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"kais","sideBox":"Learn more about [Knowledge and Information Systems](http://link.springer.com/journal/10115)","snPcode":"10115","submissionUrl":"https://submission.nature.com/new-submission/10115/3","title":"Knowledge and Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Multimodal recommendation, Multi-Preference, graph structure learning","lastPublishedDoi":"10.21203/rs.3.rs-4333408/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4333408/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Multimodal recommendation systems aim to capture diverse user preferences through data such as text and images, offering more personalized recommendation services. Accurately grasping user preferences can enhance the precision of recommendations and augment the user experience. Existing models often exploit the external attributes of item to capture users' preferences while neglecting their intrinsic attributes, such as ease of cleaning and cost-effectiveness, which are revealed in reviews. These attributes often reveal themselves in overlooked reviews. However, directly incorporating reviews into the representation will bring additional noise. Therefore, we propose the Personalized Multi-Preference Recommender (PMPR) model, which integrates reviews with multimodal data to extract multifaceted user preferences, enhancing the personalization of recommendations. Specifically, we designed a heterogeneous graph learning module based on reviews and a homogeneous graph learning module that combines the review features with multimodal features to capture users' diverse preferences. Considering the varying informational content of reviews, PMPR processes each review individually and utilizes user IDs to generate review attention vectors for aggregating the review features to reduce review noise. Finally, we integrate the Top-K method for recommendation. We compare common review processing methods with PMPR's approach to validate its effectiveness. In comparative analyses across three publicly available datasets, our enhanced model consistently demonstrated superior performance when benchmarked against seven widely recognized models. The results indicate a noteworthy improvement over the current State-of-the-Art (SOTA) model, ranging from 2.76\\% to 22.52\\% in terms of average performance.","manuscriptTitle":"Enhanced Multimodal Recommendation Systems through Reviews Integration","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-31 06:40:00","doi":"10.21203/rs.3.rs-4333408/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-09-30T00:33:14+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-29T13:35:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-05T10:55:06+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-27T09:54:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"119105419758010231760252059853024718642","date":"2024-08-20T11:21:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"260362187411883026952976826184635670215","date":"2024-08-19T09:51:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"47308387439493803720707815986166849087","date":"2024-08-18T16:30:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"171473452287430712695363848004936371798","date":"2024-08-18T13:04:22+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"310444455100948664193180807270708655944","date":"2024-08-18T04:05:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"129314774246673634611749398018093146195","date":"2024-08-16T13:44:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"70177836101621365581176350081013220762","date":"2024-08-16T13:10:48+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-06-04T17:05:29+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-05-21T11:58:32+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-04-29T09:40:36+00:00","index":"","fulltext":""},{"type":"submitted","content":"Knowledge and Information Systems","date":"2024-04-27T09:31:43+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"knowledge-and-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"kais","sideBox":"Learn more about [Knowledge and Information Systems](http://link.springer.com/journal/10115)","snPcode":"10115","submissionUrl":"https://submission.nature.com/new-submission/10115/3","title":"Knowledge and Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"3dc116bb-1491-4656-8c2b-fed1dbb30809","owner":[],"postedDate":"May 31st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-01-20T16:03:33+00:00","versionOfRecord":{"articleIdentity":"rs-4333408","link":"https://doi.org/10.1007/s10115-024-02309-x","journal":{"identity":"knowledge-and-information-systems","isVorOnly":false,"title":"Knowledge and Information Systems"},"publishedOn":"2025-01-13 15:57:45","publishedOnDateReadable":"January 13th, 2025"},"versionCreatedAt":"2024-05-31 06:40:00","video":"","vorDoi":"10.1007/s10115-024-02309-x","vorDoiUrl":"https://doi.org/10.1007/s10115-024-02309-x","workflowStages":[]},"version":"v1","identity":"rs-4333408","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4333408","identity":"rs-4333408","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}