{"id":"https://openalex.org/W4400397470","doi":"https://doi.org/10.1145/3640794.3665541","title":"Multimodal Dialog Act Classification for Digital Character Conversations","display_name":"Multimodal Dialog Act Classification for Digital Character Conversations","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4400397470","doi":"https://doi.org/10.1145/3640794.3665541"},"language":"en","primary_location":{"id":"doi:10.1145/3640794.3665541","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3640794.3665541","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Conversational User Interfaces 2024","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021147268","display_name":"Philine Witzig","orcid":"https://orcid.org/0009-0004-9782-8118"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Philine Witzig","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0004-9782-8118","affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088547723","display_name":"Rares Constantin","orcid":"https://orcid.org/0000-0002-3458-5663"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Rares Constantin","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-3458-5663","affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061306069","display_name":"Nikola Kova\u010devi\u0107","orcid":"https://orcid.org/0000-0002-1337-7670"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nikola Kovacevic","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-1337-7670","affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015553607","display_name":"Rafael Wampfler","orcid":"https://orcid.org/0000-0003-0158-1305"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Rafael Wampfler","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-0158-1305","affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":3.3642,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.92201933,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9991999864578247,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9983000159263611,"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/T12128","display_name":"AI in Service Interactions","score":0.9934999942779541,"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/dialog-box","display_name":"Dialog box","score":0.7497662901878357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7470741271972656},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6993803381919861},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5108077526092529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43874505162239075},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.374234676361084},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27278727293014526}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7497662901878357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470741271972656},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6993803381919861},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5108077526092529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43874505162239075},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.374234676361084},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27278727293014526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3640794.3665541","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3640794.3665541","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Conversational User Interfaces 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3065759762","display_name":null,"funder_award_id":"PZ00P2_216294","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1650169135","https://openalex.org/W1976855405","https://openalex.org/W2029996593","https://openalex.org/W2111754733","https://openalex.org/W2128970689","https://openalex.org/W2164598857","https://openalex.org/W2194775991","https://openalex.org/W2394990819","https://openalex.org/W2401527985","https://openalex.org/W2531638282","https://openalex.org/W2605987575","https://openalex.org/W2963550483","https://openalex.org/W2963765493","https://openalex.org/W2963968160","https://openalex.org/W2997075693","https://openalex.org/W2997174602","https://openalex.org/W3001071799","https://openalex.org/W3015783745","https://openalex.org/W3088631780","https://openalex.org/W3093400813","https://openalex.org/W3116705004","https://openalex.org/W3157070662","https://openalex.org/W3198482860","https://openalex.org/W3203140070","https://openalex.org/W3216611150","https://openalex.org/W4231807801","https://openalex.org/W4235073904","https://openalex.org/W4372260474","https://openalex.org/W4391156274"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W2283130723","https://openalex.org/W103938586","https://openalex.org/W2104718772","https://openalex.org/W4233992201","https://openalex.org/W2292950558","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Dialog":[0],"act":[1,70],"classification":[2,71],"is":[3],"essential":[4],"for":[5,133],"enabling":[6],"digital":[7,147],"characters":[8],"to":[9,14,18,36,93],"understand":[10],"and":[11,21,136],"respond":[12],"effectively":[13],"user":[15],"intents,":[16],"leading":[17],"more":[19],"engaging":[20],"seamless":[22],"interactions.":[23],"Previous":[24],"research":[25],"has":[26],"focused":[27],"on":[28,60,84],"classifying":[29],"dialog":[30,54,69,80],"acts":[31,81],"from":[32,56],"transcriptions":[33],"alone":[34],"due":[35],"missing":[37],"multimodal":[38,48,67,127],"data.":[39],"We":[40,73],"close":[41],"this":[42],"gap":[43],"by":[44,99],"collecting":[45],"a":[46,65,88,112],"new":[47,126],"(i.e.,":[49],"text,":[50],"audio,":[51],"video)":[52],"dyadic":[53],"dataset":[55],"60":[57],"participants.":[58],"Based":[59],"our":[61,76,125],"dataset,":[62,128],"we":[63,129],"developed":[64],"novel":[66],"Transformer-based":[68],"model.":[72],"show":[74],"that":[75,108,140],"model":[77],"can":[78],"predict":[79],"in":[82],"real-time":[83],"four":[85],"classes":[86],"with":[87,115,146],"Macro":[89],"F1":[90],"score":[91],"up":[92],"80.81,":[94],"outperforming":[95],"the":[96,109,116,131,142],"unimodal":[97],"baseline":[98],"<?TeX":[100],"$1.24\\%$?>":[101],"Math":[102],"1":[103],".":[104],"Our":[105],"analysis":[106],"shows":[107],"segments":[110],"of":[111,144],"sentence":[113],"associated":[114],"highest":[117],"acoustic":[118],"energy":[119],"are":[120],"most":[121],"predictive.":[122],"By":[123],"harnessing":[124],"pave":[130],"way":[132],"dynamic,":[134],"real-time,":[135],"contextually":[137],"rich":[138],"conversations":[139],"enhance":[141],"experience":[143],"interactions":[145],"characters.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
