{"id":"https://openalex.org/W7147595921","doi":"https://doi.org/10.1016/j.array.2026.100788","title":"Addressing contextual sparsity in multimodal emotion recognition using speaker-focused LLM contextualization and emotion-driven augmentation","display_name":"Addressing contextual sparsity in multimodal emotion recognition using speaker-focused LLM contextualization and emotion-driven augmentation","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7147595921","doi":"https://doi.org/10.1016/j.array.2026.100788"},"language":"en","primary_location":{"id":"doi:10.1016/j.array.2026.100788","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.array.2026.100788","pdf_url":null,"source":{"id":"https://openalex.org/S4210194039","display_name":"Array","issn_l":"2590-0056","issn":["2590-0056"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Array","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.array.2026.100788","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018772180","display_name":"Aruna Gladys A.","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101314","display_name":"SRM Dental College","ror":"https://ror.org/01bd1sf38","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210101314"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aruna Gladys A.","raw_affiliation_strings":["Department of Computer Science and Engineering(AI&ML), Easwari Engineering College, Ramapuram, Chennai, 600089, Tamil Nadu, India"],"raw_orcid":"https://orcid.org/0000-0003-2529-0983","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering(AI&ML), Easwari Engineering College, Ramapuram, Chennai, 600089, Tamil Nadu, India","institution_ids":["https://openalex.org/I4210101314"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125389376","display_name":"Vetriselvi V","orcid":null},"institutions":[{"id":"https://openalex.org/I33585257","display_name":"Anna University, Chennai","ror":"https://ror.org/01qhf1r47","country_code":"IN","type":"education","lineage":["https://openalex.org/I33585257"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vetriselvi V.","raw_affiliation_strings":["Department of Computer Science and Engineering, College of Engineering Guindy, Anna University, Chennai, 600025, Tamil Nadu, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, College of Engineering Guindy, Anna University, Chennai, 600025, Tamil Nadu, India","institution_ids":["https://openalex.org/I33585257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132641023","display_name":"Baskar P.N.","orcid":null},"institutions":[{"id":"https://openalex.org/I33585257","display_name":"Anna University, Chennai","ror":"https://ror.org/01qhf1r47","country_code":"IN","type":"education","lineage":["https://openalex.org/I33585257"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Baskar P.N.","raw_affiliation_strings":["Department of Computer Science and Engineering, College of Engineering Guindy, Anna University, Chennai, 600025, Tamil Nadu, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, College of Engineering Guindy, Anna University, Chennai, 600025, Tamil Nadu, India","institution_ids":["https://openalex.org/I33585257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048378402","display_name":"Arun Amaithi Rajan","orcid":"https://orcid.org/0000-0002-3019-5879"},"institutions":[{"id":"https://openalex.org/I33585257","display_name":"Anna University, Chennai","ror":"https://ror.org/01qhf1r47","country_code":"IN","type":"education","lineage":["https://openalex.org/I33585257"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arun Amaithi Rajan","raw_affiliation_strings":["Department of Computer Science and Engineering, College of Engineering Guindy, Anna University, Chennai, 600025, Tamil Nadu, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, College of Engineering Guindy, Anna University, Chennai, 600025, Tamil Nadu, India","institution_ids":["https://openalex.org/I33585257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018772180"],"corresponding_institution_ids":["https://openalex.org/I4210101314"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74386503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"100788","last_page":"100788"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9488000273704529,"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":0.9488000273704529,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.029600000008940697,"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/T12488","display_name":"Mental Health via Writing","score":0.0038999998942017555,"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/contextualization","display_name":"Contextualization","score":0.828499972820282},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7825999855995178},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6266999840736389},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6144000291824341},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5738000273704529},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47940000891685486},{"id":"https://openalex.org/keywords/coarticulation","display_name":"Coarticulation","score":0.47040000557899475},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4641000032424927}],"concepts":[{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.828499972820282},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7825999855995178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6693000197410583},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6266999840736389},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6144000291824341},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5738000273704529},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.47040000557899475},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4629000127315521},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44440001249313354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4277999997138977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41449999809265137},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3407000005245209},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29499998688697815},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C10646191","wikidata":"https://www.wikidata.org/wiki/Q1996523","display_name":"Dialogical self","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.array.2026.100788","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.array.2026.100788","pdf_url":null,"source":{"id":"https://openalex.org/S4210194039","display_name":"Array","issn_l":"2590-0056","issn":["2590-0056"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Array","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.array.2026.100788","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.array.2026.100788","pdf_url":null,"source":{"id":"https://openalex.org/S4210194039","display_name":"Array","issn_l":"2590-0056","issn":["2590-0056"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Array","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2091425152","https://openalex.org/W2146334809","https://openalex.org/W4283331170","https://openalex.org/W4293154800","https://openalex.org/W4378194758","https://openalex.org/W4385989098","https://openalex.org/W4389395682","https://openalex.org/W4393198193","https://openalex.org/W4402172635","https://openalex.org/W4404449818","https://openalex.org/W4410118057","https://openalex.org/W4412438081","https://openalex.org/W4414867189","https://openalex.org/W7125603131"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Emotion":[1],"Recognition":[2],"in":[3,90,122,139,184,195],"Conversations":[4],"(ERC)":[5],"faces":[6],"certain":[7],"challenges":[8],"due":[9],"to":[10,58,97,211],"the":[11,41,75,92,102,161,166,172],"contextual":[12],"sparsity":[13,200],"and":[14,80,116,130,159,177,205,226],"class":[15],"imbalance":[16],"of":[17,43,77,174,216],"rare":[18,98,141,220],"emotions,":[19],"which":[20],"are":[21,65],"often":[22],"diluted":[23],"by":[24],"frequent":[25],"neutral":[26],"or":[27],"common":[28],"emotional":[29],"expressions.":[30],"To":[31],"address":[32],"this,":[33],"we":[34],"propose":[35],"a":[36,52,189],"data-centric":[37,190],"framework":[38,191],"that":[39,95,119,133],"enhances":[40],"representation":[42],"underrepresented":[44,236],"emotions":[45,99,121],"via":[46,223],"context-aware":[47,182,214],"augmentation.":[48],"Our":[49],"approach":[50],"uses":[51],"fine-tuned":[53],"7B":[54],"Small":[55],"Language":[56],"Model":[57],"generate":[59,212],"emotion-induced":[60],"conversation":[61],"summaries.":[62],"These":[63],"summaries":[64,215],"further":[66],"utilized":[67],"for":[68,180,192,235],"soft":[69,178,203],"context":[70,199],"injection":[71],"during":[72],"augmentation,":[73],"guiding":[74],"generation":[76],"utterance":[78],"paraphrases":[79],"corresponding":[81],"expressive":[82,227],"speech":[83,86,117],"using":[84,201],"neural":[85],"synthesis.":[87],"This":[88],"helps":[89],"augmenting":[91],"dialogue":[93],"turns":[94],"belong":[96],"rather":[100],"than":[101],"entire":[103],"conversation.":[104],"A":[105],"multimodal":[106],"autoencoder-based":[107],"fusion":[108],"model":[109],"is":[110],"then":[111],"trained":[112],"on":[113,125],"text,":[114],"summaries,":[115],"embeddings":[118],"identify":[120],"conversations.":[123,196],"Experiments":[124],"benchmark":[126],"datasets":[127],"(MELD,":[128],"EmoryNLP,":[129],"IEMOCAP)":[131],"demonstrate":[132],"our":[134],"method":[135],"achieves":[136],"significant":[137],"improvements":[138],"detecting":[140],"emotion":[142,193,221,237],"classes":[143,222],"(":[144],"F":[145],"1":[146],"s":[147],"c":[148],"o":[149],"r":[150],"e":[151],">":[152],"35":[153],"%":[154],"),":[155],"outperforming":[156],"existing":[157],"baselines,":[158],"at":[160],"same":[162],"time":[163],"without":[164],"degrading":[165],"overall":[167],"accuracy.":[168],"The":[169],"results":[170],"show":[171],"effectiveness":[173],"generative":[175],"augmentation":[176],"prompting":[179,204],"building":[181],"solutions":[183],"affective":[185],"computing.":[186],"\u2022":[187,197,208,218,229],"Proposed":[188],"recognition":[194],"Addressed":[198],"LLM-guided":[202],"speaker":[206],"cues.":[207],"Fine-tuned":[209],"LLMs":[210],"emotion-rich,":[213],"utterances.":[217],"Enhanced":[219],"LLM-based":[224],"paraphrasing":[225],"speech.":[228],"Achieved":[230],"notable":[231],"F1":[232],"gains,":[233],"especially":[234],"classes.":[238]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}