{"id":"https://openalex.org/W7126407770","doi":"https://doi.org/10.3390/computers15020077","title":"A Multimodal Transformer-Based Framework for Emotion Analysis in Multilingual Video Content","display_name":"A Multimodal Transformer-Based Framework for Emotion Analysis in Multilingual Video Content","publication_year":2026,"publication_date":"2026-02-01","ids":{"openalex":"https://openalex.org/W7126407770","doi":"https://doi.org/10.3390/computers15020077"},"language":"en","primary_location":{"id":"doi:10.3390/computers15020077","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15020077","pdf_url":"https://www.mdpi.com/2073-431X/15/2/77/pdf?version=1769928812","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-431X/15/2/77/pdf?version=1769928812","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118838945","display_name":"Sehmus Yakut","orcid":null},"institutions":[{"id":"https://openalex.org/I4101805","display_name":"Y\u0131ld\u0131z Technical University","ror":"https://ror.org/0547yzj13","country_code":"TR","type":"education","lineage":["https://openalex.org/I4101805"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Sehmus Yakut","raw_affiliation_strings":["Department of Computer Engineering, Yildiz Technical University, 34220 Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0009-0002-9923-9590","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Yildiz Technical University, 34220 Istanbul, Turkey","institution_ids":["https://openalex.org/I4101805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118838946","display_name":"Yusuf Taha Tuten","orcid":null},"institutions":[{"id":"https://openalex.org/I4101805","display_name":"Y\u0131ld\u0131z Technical University","ror":"https://ror.org/0547yzj13","country_code":"TR","type":"education","lineage":["https://openalex.org/I4101805"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Yusuf Taha Tuten","raw_affiliation_strings":["Department of Computer Engineering, Yildiz Technical University, 34220 Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0009-0003-0377-1310","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Yildiz Technical University, 34220 Istanbul, Turkey","institution_ids":["https://openalex.org/I4101805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118834732","display_name":"Eren Caglar","orcid":null},"institutions":[{"id":"https://openalex.org/I202575966","display_name":"Central Bank of the Republic of Turkey","ror":"https://ror.org/01h4f0m46","country_code":"TR","type":"other","lineage":["https://openalex.org/I202575966"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Eren Caglar","raw_affiliation_strings":["R&D Center, Aktif Bank, 34220 Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R&D Center, Aktif Bank, 34220 Istanbul, Turkey","institution_ids":["https://openalex.org/I202575966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036873257","display_name":"Mehmet S. Akta\u015f","orcid":"https://orcid.org/0000-0001-7908-5067"},"institutions":[{"id":"https://openalex.org/I4101805","display_name":"Y\u0131ld\u0131z Technical University","ror":"https://ror.org/0547yzj13","country_code":"TR","type":"education","lineage":["https://openalex.org/I4101805"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mehmet S. Aktas","raw_affiliation_strings":["Department of Computer Engineering, Yildiz Technical University, 34220 Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-7908-5067","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Yildiz Technical University, 34220 Istanbul, Turkey","institution_ids":["https://openalex.org/I4101805"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5118838945","https://openalex.org/A5118838946"],"corresponding_institution_ids":["https://openalex.org/I4101805"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":24.2382,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98169611,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"15","issue":"2","first_page":"77","last_page":"77"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13219","display_name":"Mind wandering and attention","score":0.0026000000070780516,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6845999956130981},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.4876999855041504},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.39989998936653137},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.39100000262260437},{"id":"https://openalex.org/keywords/cognitive-architecture","display_name":"Cognitive architecture","score":0.3864000141620636},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3668000102043152},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.357699990272522},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.3375999927520752},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.33239999413490295}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6845999956130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6780999898910522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5723000168800354},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.3864000141620636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38089999556541443},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.357699990272522},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.28529998660087585},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2734000086784363},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/computers15020077","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15020077","pdf_url":"https://www.mdpi.com/2073-431X/15/2/77/pdf?version=1769928812","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0608a013004c4edda615b9dbf447c7c3","is_oa":false,"landing_page_url":"https://doaj.org/article/0608a013004c4edda615b9dbf447c7c3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"Computers, Vol 15, Iss 2, p 77 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/computers15020077","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15020077","pdf_url":"https://www.mdpi.com/2073-431X/15/2/77/pdf?version=1769928812","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126407770.pdf","grobid_xml":"https://content.openalex.org/works/W7126407770.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"research":[1],"addresses":[2],"the":[3,30,51,142,147,154,158,163],"challenge":[4],"of":[5,34,42,121,157,165],"inferring":[6],"complex":[7,115,172],"psychological":[8,45,149],"states,":[9],"including":[10],"stress,":[11],"fatigue,":[12],"anxiety,":[13],"cognitive":[14],"load,":[15],"and":[16,62,89,95,124,131,137,162],"boredom,":[17],"from":[18,50],"facial":[19,35],"expressions.":[20],"We":[21],"propose":[22],"an":[23],"interpretable,":[24],"literature-informed":[25],"emotion-weighting":[26,160],"methodology":[27],"that":[28,100],"transforms":[29],"eight-emotion":[31],"probability":[32],"outputs":[33],"emotion":[36,60],"recognition":[37],"models":[38,92,140],"into":[39],"continuous":[40],"estimates":[41],"these":[43],"five":[44],"states":[46],"using":[47],"weights":[48],"derived":[49],"Valence\u2013Arousal":[52],"framework,":[53],"providing":[54],"a":[55,80,84],"principled":[56],"bridge":[57],"between":[58],"discrete":[59,104],"predictions":[61],"higher-level":[63],"affective":[64,126,173],"constructs.":[65],"The":[66],"proposed":[67,159],"formulation":[68,161],"is":[69],"evaluated":[70,148],"across":[71,146],"six":[72],"representative":[73],"deep":[74],"learning":[75],"architectures\u2014a":[76],"baseline":[77],"CNN":[78,82],"(ResNet-50),":[79],"modern":[81],"(ConvNeXt),":[83],"hybrid":[85],"attention-based":[86],"model":[87],"(DDAMFN),":[88],"three":[90],"Transformer-based":[91],"(ViT,":[93],"BEiT,":[94],"Swin).":[96],"Our":[97],"results":[98],"demonstrate":[99],"strong":[101],"performance":[102,145],"on":[103],"FER":[105],"tasks":[106],"does":[107],"not":[108],"directly":[109],"translate":[110],"to":[111],"consistent":[112,144],"behavior":[113],"in":[114,171],"state":[116,133,174],"inference;":[117],"instead,":[118],"architectures":[119],"capable":[120],"preserving":[122],"subtle":[123],"distributed":[125],"cues":[127],"yield":[128],"more":[129],"stable":[130],"interpretable":[132],"estimates,":[134],"with":[135],"DDAMFN":[136],"Vision":[138],"Transformer":[139],"exhibiting":[141],"most":[143],"states.":[150],"These":[151],"findings":[152],"highlight":[153],"central":[155],"role":[156],"importance":[164],"architecture":[166],"selection":[167],"beyond":[168],"categorical":[169],"accuracy":[170],"analysis.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-02T00:00:00"}