{"id":"https://openalex.org/W4416017455","doi":"https://doi.org/10.1145/3746252.3761398","title":"Do Recommender Systems Really Leverage Multimodal Content? A Comprehensive Analysis on Multimodal Representations for Recommendation","display_name":"Do Recommender Systems Really Leverage Multimodal Content? A Comprehensive Analysis on Multimodal Representations for Recommendation","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017455","doi":"https://doi.org/10.1145/3746252.3761398"},"language":"en","primary_location":{"id":"doi:10.1145/3746252.3761398","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761398","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746252.3761398","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029434859","display_name":"Claudio Pomo","orcid":"https://orcid.org/0000-0001-5206-3909"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Claudio Pomo","raw_affiliation_strings":["Politecnico di Bari, Bari, Italy"],"raw_orcid":"https://orcid.org/0000-0001-5206-3909","affiliations":[{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079764541","display_name":"Matteo Attimonelli","orcid":"https://orcid.org/0009-0003-6600-1938"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Attimonelli","raw_affiliation_strings":["Politecnico di Bari, Bari, Italy and Sapienza University of Rome, Rome, Italy"],"raw_orcid":"https://orcid.org/0009-0003-6600-1938","affiliations":[{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy and Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094105787","display_name":"Danilo Danese","orcid":"https://orcid.org/0009-0000-5203-1229"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Danilo Danese","raw_affiliation_strings":["Politecnico di Bari, Bari, Italy"],"raw_orcid":"https://orcid.org/0009-0000-5203-1229","affiliations":[{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076295894","display_name":"Fedelucio Narducci","orcid":"https://orcid.org/0000-0002-9255-3256"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fedelucio Narducci","raw_affiliation_strings":["Politecnico di Bari, Bari, Italy"],"raw_orcid":"https://orcid.org/0000-0002-9255-3256","affiliations":[{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034668928","display_name":"Tommaso Di Noia","orcid":"https://orcid.org/0000-0002-0939-5462"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Tommaso Di Noia","raw_affiliation_strings":["Politecnico di Bari, Bari, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0939-5462","affiliations":[{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5029434859"],"corresponding_institution_ids":["https://openalex.org/I68618741"],"apc_list":null,"apc_paid":null,"fwci":2.2403,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9028717,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2377","last_page":"2387"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6086999773979187,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6086999773979187,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.07190000265836716,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.046300001442432404,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.8046000003814697},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7433000206947327},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5249999761581421},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.301800012588501}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8046000003814697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039000034332275},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7433000206947327},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5340999960899353},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46230000257492065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3043999969959259},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29660001397132874},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746252.3761398","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761398","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1758116","is_oa":false,"landing_page_url":"https://hdl.handle.net/11573/1758116","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3746252.3761398","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761398","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2042281163","https://openalex.org/W2054141820","https://openalex.org/W2143017621","https://openalex.org/W2158515176","https://openalex.org/W2533292283","https://openalex.org/W3131318543","https://openalex.org/W3134063549","https://openalex.org/W4282549812","https://openalex.org/W4285288414","https://openalex.org/W4312583258","https://openalex.org/W4312824836","https://openalex.org/W4386289268","https://openalex.org/W4406298996"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Recommender":[1],"Systems":[2],"aim":[3],"to":[4,90,177],"improve":[5,149],"recommendation":[6,150,185],"accuracy":[7],"by":[8],"integrating":[9],"heterogeneous":[10],"content,":[11],"such":[12,138],"as":[13,142,173],"images":[14],"and":[15,69,170,180],"textual":[16,128],"metadata.":[17],"While":[18],"effective,":[19],"it":[20],"remains":[21],"unclear":[22],"whether":[23],"their":[24,134],"gains":[25],"stem":[26],"from":[27,56],"true":[28],"multimodal":[29,41,135,182],"understanding":[30],"or":[31],"increased":[32],"model":[33],"complexity.":[34],"This":[35,97],"work":[36],"investigates":[37],"the":[38,45,49,154,164],"role":[39],"of":[40,48,133,166],"item":[42],"embeddings,":[43],"emphasizing":[44],"semantic":[46,155],"informativeness":[47],"representations.":[50],"Initial":[51],"experiments":[52],"reveal":[53],"that":[54,74],"embeddings":[55,93,117],"standard":[57],"extractors":[58],"(e.g.,":[59],"ResNet50,":[60],"Sentence-Bert)":[61],"enhance":[62],"performance,":[63,151],"but":[64],"rely":[65],"on":[66],"modality-specific":[67],"encoders":[68],"ad":[70],"hoc":[71],"fusion":[72],"strategies":[73],"lack":[75],"control":[76],"over":[77],"cross-modal":[78],"alignment.":[79],"To":[80],"overcome":[81],"these":[82],"limitations,":[83],"we":[84],"leverage":[85],"Large":[86],"Vision-Language":[87],"Models":[88],"(LVLMs)":[89],"generate":[91],"multimodal-by-design":[92],"via":[94],"structured":[95,127],"prompts.":[96],"approach":[98],"yields":[99],"semantically":[100,167],"aligned":[101],"representations":[102,169,183],"without":[103],"requiring":[104],"any":[105],"fusion.":[106],"Experiments":[107],"across":[108],"multiple":[109],"settings":[110],"show":[111],"notable":[112],"performance":[113],"improvements.":[114],"Furthermore,":[115],"LVLMs":[116,159,172],"offer":[118],"a":[119,174],"distinctive":[120],"advantage:":[121],"they":[122,148],"can":[123],"be":[124],"decoded":[125],"into":[126,145],"descriptions,":[129],"enabling":[130],"direct":[131],"assessment":[132],"comprehension.":[136],"When":[137],"descriptions":[139],"are":[140],"incorporated":[141],"side":[143],"content":[144],"recommender":[146],"systems,":[147],"empirically":[152],"validating":[153],"alignment":[156],"encoded":[157],"in":[158,184],"outputs.":[160],"Our":[161],"study":[162],"highlights":[163],"importance":[165],"rich":[168],"positions":[171],"compelling":[175],"foundation":[176],"build":[178],"robust":[179],"meaningful":[181],"tasks.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-11-08T00:00:00"}