{"id":"https://openalex.org/W4319862459","doi":"https://doi.org/10.1109/slt54892.2023.10022548","title":"On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis","display_name":"On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862459","doi":"https://doi.org/10.1109/slt54892.2023.10022548"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022548","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061074419","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0002-3971-0654"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080550833","display_name":"Akihiko Takashima","orcid":"https://orcid.org/0000-0001-7361-4562"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiko Takashima","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063110877","display_name":"Satoshi Suzuki","orcid":"https://orcid.org/0000-0002-1423-3767"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Suzuki","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082466886","display_name":"Naoki Makishima","orcid":"https://orcid.org/0000-0002-7065-315X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Makishima","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103222069","display_name":"Keita Suzuki","orcid":"https://orcid.org/0009-0006-7963-3952"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keita Suzuki","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033975068","display_name":"Takanori Ashihara","orcid":"https://orcid.org/0009-0003-4322-4127"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanori Ashihara","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049917170","display_name":"Hiroshi Sat\u014d","orcid":"https://orcid.org/0000-0002-5899-1340"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Sato","raw_affiliation_strings":["NTT Corporation"],"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5061074419"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":1.0173,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.74128058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"739","last_page":"746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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/encoder","display_name":"Encoder","score":0.8451298475265503},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8076329231262207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8015498518943787},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5915734767913818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5558760166168213},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5378014445304871},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5111716389656067},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.461095929145813},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4468629062175751},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4460511803627014},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4276474118232727},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41029495000839233},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3247354328632355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07106244564056396}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8451298475265503},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8076329231262207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015498518943787},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5915734767913818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5558760166168213},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5378014445304871},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5111716389656067},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.461095929145813},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4468629062175751},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4460511803627014},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4276474118232727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41029495000839233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3247354328632355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07106244564056396},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022548","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2341528187","https://openalex.org/W2556418146","https://openalex.org/W2883409523","https://openalex.org/W2886193235","https://openalex.org/W2891399311","https://openalex.org/W2936774411","https://openalex.org/W2948947170","https://openalex.org/W2962931510","https://openalex.org/W2963710346","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964216663","https://openalex.org/W2970597249","https://openalex.org/W3034266838","https://openalex.org/W3036601975","https://openalex.org/W3093051361","https://openalex.org/W3101998545","https://openalex.org/W3128412859","https://openalex.org/W3163841364","https://openalex.org/W3199964822","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224933771","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6752724743","https://openalex.org/W6755207826","https://openalex.org/W6763701032","https://openalex.org/W6774314701","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2004831463","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"This":[0,45],"paper":[1,46],"investigates":[2],"the":[3,18,48,62,116,119,123,128],"effectiveness":[4,19],"and":[5,38,75,80,106],"implementation":[6],"of":[7,20,61,118,122,127],"modality-specific":[8],"large-scale":[9,52],"pre-trained":[10,21,53,64,93],"encoders":[11,22,54,65,94,124],"for":[12,34,68,77],"multimodal":[13,107],"sentiment":[14],"analysis":[15],"(MSA).":[16],"Although":[17],"in":[23,103],"various":[24],"fields":[25],"has":[26,41],"been":[27,43],"reported,":[28],"conventional":[29,56,101],"MSA":[30],"methods":[31,90],"employ":[32],"them":[33],"only":[35],"linguistic":[36,81],"modality,":[37],"their":[39],"application":[40],"not":[42],"investigated.":[44],"compares":[47],"features":[49,102],"yielded":[50],"by":[51],"with":[55,91,100],"heuristic":[57],"features.":[58],"One":[59],"each":[60,69],"largest":[63],"publicly":[66],"available":[67,134],"modality":[70],"are":[71,133],"used;":[72],"CLIP-ViT,":[73],"WavLM,":[74],"BERT":[76],"visual,":[78],"acoustic,":[79],"modalities,":[82],"respectively.":[83],"Experiments":[84],"on":[85],"two":[86],"datasets":[87],"reveal":[88],"that":[89],"domain-specific":[92],"attain":[95],"better":[96,113],"performance":[97],"than":[98,125],"those":[99,126],"both":[104],"unimodal":[105],"scenarios.":[108],"We":[109],"also":[110],"find":[111],"it":[112],"to":[114],"use":[115],"outputs":[117],"intermediate":[120],"layers":[121],"output":[129],"layer.":[130],"The":[131],"codes":[132],"at":[135],"https://github.com/ando-hub/MSA_Pretrain.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}