{"id":"https://openalex.org/W7164891855","doi":"https://doi.org/10.48550/arxiv.2606.16973","title":"How Much Do Reviews Really Contribute? A Study on Text-Enriched Matrix Factorization for Recommendations","display_name":"How Much Do Reviews Really Contribute? A Study on Text-Enriched Matrix Factorization for Recommendations","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164891855","doi":"https://doi.org/10.48550/arxiv.2606.16973"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.16973","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16973","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.16973","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074268683","display_name":"Eduardo Ferreira da Silva","orcid":"https://orcid.org/0000-0002-3019-8471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"da Silva, Eduardo Ferreira","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108977939","display_name":"Mayki dos Santos Oliveira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliveira, Mayki dos Santos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138718344","display_name":"Joel Machado Pires Denis Dantas Boaventura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boaventura, Joel Machado Pires Denis Dantas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138753068","display_name":"Frederico Ara\u00fajo Dur\u00e3o","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dur\u00e3o, Frederico Ara\u00fajo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.6028000116348267,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.6028000116348267,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.10729999840259552,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1031000018119812,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5727999806404114},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5694000124931335},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.4837999939918518},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.48339998722076416},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.43560001254081726},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.43130001425743103},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.31139999628067017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522000074386597},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5727999806404114},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5694000124931335},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5333999991416931},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.4837999939918518},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.48339998722076416},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39800000190734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38769999146461487},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.3050999939441681},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.16973","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16973","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.16973","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.16973","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7297861576080322}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Incorporating":[0],"textual":[1,46,75,123,155,175],"reviews":[2],"into":[3,209],"a":[4,9,59,66,110],"Recommender":[5],"System":[6],"has":[7],"become":[8],"prominent":[10],"strategy":[11],"for":[12,201],"enriching":[13],"collaborative":[14,33,61,73,128,182,192],"signals":[15,76,176,208],"with":[16,127,136,144,152],"semantic":[17,206],"information.":[18],"However,":[19],"the":[20,43,117,122,171,181,202],"actual":[21],"contribution":[22,173],"of":[23,45,121,174,205],"review-derived":[24],"representations":[25,103],"remains":[26,177],"an":[27],"open":[28],"question,":[29],"particularly":[30],"when":[31],"strong":[32],"baselines":[34],"are":[35],"employed.":[36],"In":[37],"this":[38],"work,":[39],"we":[40,64,108],"systematically":[41],"investigate":[42],"impact":[44],"information":[47,193],"on":[48],"Matrix":[49],"Factorization":[50],"by":[51],"introducing":[52],"and":[53,74,95,98,115,139,146,150],"comparing":[54],"three":[55],"enrichment":[56],"strategies":[57],"over":[58,154],"common":[60],"backbone.":[62,183],"First,":[63],"propose":[65],"learnable":[67],"gating":[68],"mechanism":[69,80,112],"that":[70,113,163],"adaptively":[71],"balances":[72],"during":[77],"training.":[78],"This":[79],"is":[81],"applied":[82],"to":[83,180,195],"two":[84],"distinct":[85],"review":[86,207],"representations:":[87],"(i)":[88],"aggregated":[89],"topic":[90,137],"profiles":[91,138],"extracted":[92],"from":[93,105],"user":[94],"item":[96],"histories,":[97],"(ii)":[99],"full":[100],"text":[101,140,147],"embedding":[102],"derived":[104],"reviews.":[106],"Additionally,":[107],"explore":[109],"cross-attention":[111,153],"identifies":[114],"emphasizes":[116],"most":[118],"informative":[119],"dimensions":[120],"representation":[124,169],"before":[125],"fusion":[126,166],"factors.":[129],"We":[130],"evaluate":[131],"six":[132],"variants:":[133],"pure,":[134],"enriched":[135,143],"via":[141,148],"gating;":[142,149],"topics":[145],"enhanced":[151],"features.":[156],"Experiments":[157],"across":[158],"multiple":[159],"review-based":[160],"datasets":[161],"reveal":[162],"although":[164],"adaptive":[165],"mechanisms":[167],"improve":[168],"flexibility,":[170],"marginal":[172],"limited":[178],"compared":[179],"These":[184],"findings":[185],"suggest":[186],"that,":[187],"under":[188],"typical":[189],"rating-prediction":[190],"settings,":[191],"continues":[194],"dominate":[196],"performance,":[197],"raising":[198],"important":[199],"considerations":[200],"effective":[203],"integration":[204],"recommendation":[210],"models.":[211]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-17T00:00:00"}