{"id":"https://openalex.org/W4414394878","doi":"https://doi.org/10.3724/2096-7004.di.2025.0118","title":"CoTMSD: Leveraging Chain-of-Thought for Multimodal Sarcasm Detection","display_name":"CoTMSD: Leveraging Chain-of-Thought for Multimodal Sarcasm Detection","publication_year":2025,"publication_date":"2025-08-10","ids":{"openalex":"https://openalex.org/W4414394878","doi":"https://doi.org/10.3724/2096-7004.di.2025.0118"},"language":"en","primary_location":{"id":"doi:10.3724/2096-7004.di.2025.0118","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0118","pdf_url":"https://www.sciengine.com/doi/pdf/26ABF3019C4D4F1DA46A767D0D88E962","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.sciengine.com/doi/pdf/26ABF3019C4D4F1DA46A767D0D88E962","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100331710","display_name":"Xu Liu","orcid":"https://orcid.org/0000-0002-8780-5455"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100830970","display_name":"Xiangdong Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangdong Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392353","display_name":"Li Jiang","orcid":"https://orcid.org/0000-0001-7058-6957"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088080995","display_name":"\u88d5\u7f8e\u5b50 \u5897\u7530","orcid":"https://orcid.org/0009-0002-2228-1619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021545074","display_name":"Tian Lan","orcid":"https://orcid.org/0000-0002-8907-2603"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Lan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22157243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"2","first_page":"20250118","last_page":"20250118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9277999997138977,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9277999997138977,"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","display_name":"Sarcasm","score":0.9681000113487244},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7577000260353088},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6340000033378601},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3790999948978424},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.31150001287460327},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.29510000348091125}],"concepts":[{"id":"https://openalex.org/C2776207355","wikidata":"https://www.wikidata.org/wiki/Q191035","display_name":"Sarcasm","level":3,"score":0.9681000113487244},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7577000260353088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7276999950408936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6815999746322632},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6340000033378601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5494999885559082},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46720001101493835},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3790999948978424},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3724/2096-7004.di.2025.0118","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0118","pdf_url":"https://www.sciengine.com/doi/pdf/26ABF3019C4D4F1DA46A767D0D88E962","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3724/2096-7004.di.2025.0118","is_oa":true,"landing_page_url":"https://doi.org/10.3724/2096-7004.di.2025.0118","pdf_url":"https://www.sciengine.com/doi/pdf/26ABF3019C4D4F1DA46A767D0D88E962","source":{"id":"https://openalex.org/S4210186383","display_name":"Data Intelligence","issn_l":"2096-7004","issn":["2096-7004","2641-435X"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414394878.pdf","grobid_xml":"https://content.openalex.org/works/W4414394878.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"sarcasm":[1,120],"detection":[2,121],"models":[3,42],"often":[4],"suffer":[5],"from":[6],"overfitting":[7],"on":[8,131],"in-domain":[9],"data":[10,23],"due":[11],"to":[12,28,37,48,61,85],"the":[13,20,81,102],"lack":[14],"of":[15,89,136],"accurate":[16],"external":[17,78],"knowledge":[18,46,51,79],"and":[19,74,110],"relatively":[21],"low-quality":[22],"in":[24,55,113],"existing":[25],"benchmarks,":[26],"leading":[27],"poor":[29],"model":[30],"robustness.":[31],"To":[32],"address":[33],"this,":[34],"we":[35,66],"propose":[36],"use":[38],"multimodal":[39],"large":[40],"language":[41],"(MLLMs)":[43],"as":[44],"a":[45,68,132],"source":[47],"extract":[49],"relevant":[50],"step":[52],"by":[53],"step,":[54],"which":[56],"Chain-of-Thought":[57],"(CoT)":[58],"is":[59],"used":[60],"understand":[62],"rich":[63],"semantics.":[64,91],"Additionally,":[65],"design":[67],"multi-stage":[69],"fusion":[70],"module":[71],"that":[72,95,123],"interactively":[73],"incrementally":[75],"integrates":[76],"generated":[77],"with":[80],"original":[82],"data,":[83],"aiming":[84],"uncover":[86],"deeper":[87],"levels":[88],"sarcastic":[90],"Extensive":[92],"experiments":[93],"show":[94],"our":[96,117],"approach":[97],"not":[98],"only":[99],"significantly":[100],"advances":[101],"state-of-theart":[103],"results":[104],"but":[105],"also":[106],"demonstrates":[107],"exceptional":[108],"robustness":[109],"noise":[111],"resistance":[112],"out-of-domain":[114],"scenarios.":[115],"Furthermore,":[116],"method":[118],"exhibits":[119],"capabilities":[122],"substantially":[124],"outperform":[125],"other":[126],"models,":[127],"even":[128],"when":[129],"trained":[130],"very":[133],"limited":[134],"amount":[135],"data.":[137]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}