{"id":"https://openalex.org/W4387355348","doi":"https://doi.org/10.48550/arxiv.2310.01430","title":"Sarcasm in Sight and Sound: Benchmarking and Expansion to Improve Multimodal Sarcasm Detection","display_name":"Sarcasm in Sight and Sound: Benchmarking and Expansion to Improve Multimodal Sarcasm Detection","publication_year":2023,"publication_date":"2023-09-29","ids":{"openalex":"https://openalex.org/W4387355348","doi":"https://doi.org/10.48550/arxiv.2310.01430"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.01430","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.01430","pdf_url":"https://arxiv.org/pdf/2310.01430","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.01430","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009006680","display_name":"Swapnil Bhosale","orcid":"https://orcid.org/0000-0001-8299-7569","observed_orcids":["https://orcid.org/0000-0001-8299-7569"]},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bhosale, Swapnil","raw_affiliation_strings":["University of Surrey , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey , UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085117078","display_name":"Abhra Chaudhuri","orcid":"https://orcid.org/0009-0004-3723-668X","observed_orcids":["https://orcid.org/0009-0004-3723-668X"]},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chaudhuri, Abhra","raw_affiliation_strings":["University of Surrey , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey , UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104178657","display_name":"Alex Lee Robert Williams","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Williams, Alex Lee Robert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011901122","display_name":"Divyank Tiwari","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tiwari, Divyank","raw_affiliation_strings":["IIT Bombay , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Bombay , India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008386240","display_name":"Anjan Dutta","orcid":"https://orcid.org/0000-0002-1667-2245","observed_orcids":["https://orcid.org/0000-0002-1667-2245"]},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dutta, Anjan","raw_affiliation_strings":["University of Surrey , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey , UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028643592","display_name":"Xiatian Zhu","orcid":"https://orcid.org/0000-0002-9284-2955","observed_orcids":["https://orcid.org/0000-0002-9284-2955"]},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhu, Xiatian","raw_affiliation_strings":["University of Surrey , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey , UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065100828","display_name":"Pushpak Bhattacharyya","orcid":"https://orcid.org/0000-0001-5319-5508","observed_orcids":["https://orcid.org/0000-0001-5319-5508"]},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bhattacharyya, Pushpak","raw_affiliation_strings":["IIT Bombay , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Bombay , India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054401662","display_name":"Diptesh Kanojia","orcid":"https://orcid.org/0000-0001-8814-0080","observed_orcids":["https://orcid.org/0000-0001-8814-0080"]},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kanojia, Diptesh","raw_affiliation_strings":["University of Surrey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9272000193595886,"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":0.9272000193595886,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.06440000236034393,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/sarcasm-detection","display_name":"sarcasm detection","score":0.9670000076293945},{"id":"https://openalex.org/keywords/mustard","display_name":"mustard","score":0.9649999737739563},{"id":"https://openalex.org/keywords/dataset-benchmarking","display_name":"dataset benchmarking","score":0.6620000004768372},{"id":"https://openalex.org/keywords/facial-expressions","display_name":"facial expressions","score":0.6610000133514404},{"id":"https://openalex.org/keywords/intonation","display_name":"intonation","score":0.7369999885559082},{"id":"https://openalex.org/keywords/tonality","display_name":"tonality","score":0.6449999809265137},{"id":"https://openalex.org/keywords/inter-annotator-agreement","display_name":"inter-annotator agreement","score":0.8270000219345093},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.4830000102519989}],"concepts":[{"id":"https://openalex.org/C2776207355","wikidata":"https://www.wikidata.org/wiki/Q191035","display_name":"Sarcasm","level":3,"score":0.9558992385864258},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8025333285331726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6969480514526367},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6773504018783569},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.5992478728294373},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5810953378677368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49448466300964355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4338929057121277},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18863964080810547},{"id":"https://openalex.org/C2779975665","wikidata":"https://www.wikidata.org/wiki/Q131361","display_name":"Irony","level":2,"score":0.13374698162078857},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.01430","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.01430","pdf_url":"https://arxiv.org/pdf/2310.01430","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.01430","doi":"https://doi.org/10.48550/arxiv.2310.01430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.01430","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.01430","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.01430","pdf_url":"https://arxiv.org/pdf/2310.01430","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387355348.pdf","grobid_xml":"https://content.openalex.org/works/W4387355348.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7102411469","https://openalex.org/W7118179001","https://openalex.org/W4386426986","https://openalex.org/W4385572183","https://openalex.org/W7140134147","https://openalex.org/W4414697279","https://openalex.org/W4411338739","https://openalex.org/W4416922359","https://openalex.org/W7171321623","https://openalex.org/W3161192968"],"abstract_inverted_index":{"The":[0,131],"introduction":[1],"of":[2,32,53,70,151,167],"the":[3,54,68,71,86,92,95,111,116,141,149,152],"MUStARD":[4],"dataset,":[5,153],"and":[6,36,38,62,122,154,170,177],"its":[7],"emotion":[8],"recognition":[9],"extension":[10,117],"MUStARD++,":[11,100],"have":[12],"identified":[13],"sarcasm":[14],"to":[15,48,77,90,148],"be":[16],"a":[17,50,80,126,137],"multi-modal":[18,72],"phenomenon":[19],"--":[20,140],"expressed":[21],"not":[22],"only":[23],"in":[24,83,94,99,165],"natural":[25],"language":[26],"text,":[27],"but":[28],"also":[29],"through":[30],"manners":[31],"speech":[33],"(like":[34],"tonality":[35],"intonation)":[37],"visual":[39,63],"cues":[40],"(facial":[41],"expression).":[42],"With":[43],"this":[44],"work,":[45],"we":[46,101,106],"aim":[47],"perform":[49],"rigorous":[51],"benchmarking":[52,110],"MUStARD++":[55],"dataset":[56],"by":[57,158],"considering":[58],"state-of-the-art":[59],"language,":[60],"speech,":[61],"encoders,":[64],"for":[65],"fully":[66],"utilizing":[67],"totality":[69],"richness":[73],"that":[74],"it":[75],"has":[76],"offer,":[78],"achieving":[79,125],"2\\%":[81],"improvement":[82],"macro-F1":[84,129],"over":[85],"existing":[87],"benchmark.":[88],"Additionally,":[89],"cure":[91],"imbalance":[93],"`sarcasm":[96],"type'":[97],"category":[98],"propose":[102],"an":[103],"extension,":[104],"which":[105,146],"call":[107],"\\emph{MUStARD++":[108],"Balanced},":[109],"same":[112],"with":[113,161],"instances":[114],"from":[115,136],"split":[118],"across":[119],"both":[120],"train":[121],"test":[123],"sets,":[124],"further":[127],"2.4\\%":[128],"boost.":[130],"new":[132],"clips":[133],"were":[134,155],"taken":[135],"novel":[138],"source":[139],"TV":[142],"show,":[143],"House":[144],"MD,":[145],"adds":[147],"diversity":[150],"manually":[156],"annotated":[157],"multiple":[159],"annotators":[160],"substantial":[162],"inter-annotator":[163],"agreement":[164],"terms":[166],"Cohen's":[168],"kappa":[169],"Krippendorf's":[171],"alpha.":[172],"Our":[173],"code,":[174],"extended":[175],"data,":[176],"SOTA":[178],"benchmark":[179],"models":[180],"are":[181],"made":[182],"public.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-22T18:32:59.640997","created_date":"2023-10-05T00:00:00"}