{"id":"https://openalex.org/W7164841453","doi":"https://doi.org/10.1145/3816713.3818220","title":"Cross-Modal Emotion Discrepancy Detection: Detecting When Voice Reveals Emotions That Text Conceals","display_name":"Cross-Modal Emotion Discrepancy Detection: Detecting When Voice Reveals Emotions That Text Conceals","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164841453","doi":"https://doi.org/10.1145/3816713.3818220"},"language":null,"primary_location":{"id":"doi:10.1145/3816713.3818220","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3816713.3818220","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Advances in Information Technology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3816713.3818220","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138635723","display_name":"Kaung Hset Hein","orcid":"https://orcid.org/0009-0000-2888-7051"},"institutions":[{"id":"https://openalex.org/I60837268","display_name":"King Mongkut's University of Technology Thonburi","ror":"https://ror.org/0057ax056","country_code":"TH","type":"education","lineage":["https://openalex.org/I60837268"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Kaung Hset Hein","raw_affiliation_strings":["School of Information Technology, King Mongkut's University of Technology Thonburi, Bangkok, Bangkok, Thailand"],"raw_orcid":"https://orcid.org/0009-0000-2888-7051","affiliations":[{"raw_affiliation_string":"School of Information Technology, King Mongkut's University of Technology Thonburi, Bangkok, Bangkok, Thailand","institution_ids":["https://openalex.org/I60837268"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111758092","display_name":"Jonathan H. Chan","orcid":"https://orcid.org/0000-0002-2384-0462"},"institutions":[{"id":"https://openalex.org/I60837268","display_name":"King Mongkut's University of Technology Thonburi","ror":"https://ror.org/0057ax056","country_code":"TH","type":"education","lineage":["https://openalex.org/I60837268"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Jonathan Chan","raw_affiliation_strings":["School of Information Technology, King Mongkut's University of Technology Thonburi, Bangkok, Thailand"],"raw_orcid":"https://orcid.org/0000-0002-2384-0462","affiliations":[{"raw_affiliation_string":"School of Information Technology, King Mongkut's University of Technology Thonburi, Bangkok, Thailand","institution_ids":["https://openalex.org/I60837268"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60837268"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.89903947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9168000221252441,"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":0.9168000221252441,"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":0.06340000033378601,"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":0.00279999990016222,"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/prosody","display_name":"Prosody","score":0.6901000142097473},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5163000226020813},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44350001215934753},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4300999939441681},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4277999997138977},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.413100004196167},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.39719998836517334},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.385699987411499},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.38530001044273376}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6901000142097473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6064000129699707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5569000244140625},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5157999992370605},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42969998717308044},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.38530001044273376},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.37560001015663147},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C2778262033","wikidata":"https://www.wikidata.org/wiki/Q5373795","display_name":"Emotional prosody","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3816713.3818220","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3816713.3818220","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Advances in Information Technology","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3816713.3818220","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3816713.3818220","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Advances in Information Technology","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2077030430","https://openalex.org/W2191779130","https://openalex.org/W2295598076","https://openalex.org/W2556418146","https://openalex.org/W2584561145","https://openalex.org/W2803193013","https://openalex.org/W2904932135","https://openalex.org/W2963686995","https://openalex.org/W4361994820","https://openalex.org/W4403262674","https://openalex.org/W4410087135"],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"multi-modal":[1,220],"emotion":[2,13,84,221],"recognition":[3],"systems":[4],"fuse":[5],"text":[6,30,58,72,177,193],"and":[7,32,81,86,102,148,157,224],"audio":[8],"to":[9,188],"improve":[10],"a":[11,36],"single":[12],"prediction":[14],"by":[15],"seeking":[16],"inter-modal":[17],"agreement.":[18],"This":[19],"work":[20],"takes":[21],"the":[22,27,47,112,140,197,209,213],"opposite":[23],"approach:":[24],"we":[25,42,65],"model":[26],"disagreement":[28],"between":[29],"sentiment":[31],"voice":[33,76,205],"prosody":[34],"as":[35,208],"signal":[37],"for":[38,154,219],"emotional":[39],"discrepancy\u2014an":[40],"approach":[41],"term":[43],"asymmetric":[44,198],"fusion.":[45],"Using":[46],"RAVDESS":[48,191],"dataset":[49],"(2,880":[50],"recordings":[51],"from":[52,74,79],"24":[53],"actors),":[54],"where":[55,192],"semantically":[56],"neutral":[57],"is":[59,194],"paired":[60],"with":[61,166],"emotionally":[62],"varied":[63,168],"speech,":[64],"extract":[66],"26":[67],"features":[68,73,78,142,173],"across":[69],"three":[70],"categories:":[71],"DistilRoBERTa,":[75],"prosodic":[77],"librosa":[80],"wav2vec2-based":[82],"speech":[83],"recognition,":[85],"cross-modal":[87,172],"discrepancy":[88],"features.":[89],"We":[90],"systematically":[91],"compare":[92],"eight":[93],"classifiers\u2014including":[94],"logistic":[95,122],"regression,":[96],"SVM,":[97],"Random":[98],"Forest,":[99],"XGBoost,":[100],"LightGBM,":[101],"Gradient":[103,109],"Boosting\u2014using":[104],"stratified":[105],"grouped":[106],"5-fold":[107],"cross-validation.":[108],"Boosting":[110],"achieves":[111],"best":[113],"performance":[114],"(F1":[115,128],"=":[116,119,129,132],"0.954,":[117],"AUC":[118,131],"0.966),":[120],"while":[121],"regression":[123],"provides":[124],"an":[125],"interpretable":[126],"alternative":[127],"0.918,":[130],"0.947).":[133],"A":[134],"feature":[135],"selection":[136],"study":[137],"reveals":[138],"that":[139,171],"top-10":[141],"match":[143],"or":[144],"exceed":[145],"full-set":[146],"performance,":[147],"per-emotion":[149],"analysis":[150,203],"shows":[151],"perfect":[152],"detection":[153],"angry,":[155],"disgust,":[156],"surprised":[158],"categories.":[159],"Cross-dataset":[160],"validation":[161],"on":[162,190],"MELD":[163],"(13,079":[164],"utterances":[165],"naturally":[167],"text)":[169],"confirms":[170],"contribute":[174],"substantially":[175],"when":[176],"content":[178],"varies":[179],"(mean":[180],"F1":[181],"improvement":[182],"of":[183,215],"+0.160":[184],"over":[185],"voice-only),":[186],"compared":[187],"+0.001":[189],"uniform,":[195],"validating":[196],"fusion":[199],"approach.":[200],"Feature":[201],"importance":[202],"identifies":[204],"energy":[206],"variation":[207],"dominant":[210],"predictor,":[211],"demonstrating":[212],"viability":[214],"interpretable,":[216],"feature-engineered":[217],"models":[218],"analysis.":[222],"Code":[223],"resources":[225],"are":[226],"publicly":[227],"available":[228],"at":[229],"https://github.com/PhilixTheExplorer/cross-modal-emotion-discrepancy.":[230]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-06-16T00:00:00"}