{"id":"https://openalex.org/W4396723401","doi":"https://doi.org/10.1145/3589334.3648143","title":"Contrastive Learning for Multimodal Classification of Crisis related Tweets","display_name":"Contrastive Learning for Multimodal Classification of Crisis related Tweets","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4396723401","doi":"https://doi.org/10.1145/3589334.3648143"},"language":"en","primary_location":{"id":"doi:10.1145/3589334.3648143","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589334.3648143","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 ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3589334.3648143","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032853619","display_name":"Bishwas Mandal","orcid":"https://orcid.org/0000-0002-6686-2223"},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bishwas Mandal","raw_affiliation_strings":["Kansas State University, Manhattan, KS, USA"],"raw_orcid":"https://orcid.org/0000-0002-6686-2223","affiliations":[{"raw_affiliation_string":"Kansas State University, Manhattan, KS, USA","institution_ids":["https://openalex.org/I189590672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007743475","display_name":"Sarthak Khanal","orcid":"https://orcid.org/0000-0002-7515-9433"},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarthak Khanal","raw_affiliation_strings":["Kansas State University, Manhattan, KS, USA"],"raw_orcid":"https://orcid.org/0000-0002-7515-9433","affiliations":[{"raw_affiliation_string":"Kansas State University, Manhattan, KS, USA","institution_ids":["https://openalex.org/I189590672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067341711","display_name":"Doina Caragea","orcid":"https://orcid.org/0000-0002-6440-0914"},"institutions":[{"id":"https://openalex.org/I189590672","display_name":"Kansas State University","ror":"https://ror.org/05p1j8758","country_code":"US","type":"education","lineage":["https://openalex.org/I189590672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Doina Caragea","raw_affiliation_strings":["Kansas State University, Manhattan, KS, USA"],"raw_orcid":"https://orcid.org/0000-0002-6440-0914","affiliations":[{"raw_affiliation_string":"Kansas State University, Manhattan, KS, USA","institution_ids":["https://openalex.org/I189590672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032853619"],"corresponding_institution_ids":["https://openalex.org/I189590672"],"apc_list":null,"apc_paid":null,"fwci":3.8626,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94007604,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4555","last_page":"4564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9980000257492065,"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":0.9980000257492065,"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/T11121","display_name":"Public Relations and Crisis Communication","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9739000201225281,"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/computer-science","display_name":"Computer science","score":0.6760692000389099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4964497685432434},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4826684296131134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6760692000389099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4964497685432434},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4826684296131134}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589334.3648143","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589334.3648143","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 ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3589334.3648143","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589334.3648143","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 ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2015587001","https://openalex.org/W2062632672","https://openalex.org/W2108598243","https://openalex.org/W2149940198","https://openalex.org/W2187089797","https://openalex.org/W2295275897","https://openalex.org/W2562892017","https://openalex.org/W2798683079","https://openalex.org/W2905587047","https://openalex.org/W2910074218","https://openalex.org/W2911588830","https://openalex.org/W2922183696","https://openalex.org/W2953072307","https://openalex.org/W2964082860","https://openalex.org/W2964514192","https://openalex.org/W2966730110","https://openalex.org/W2974087526","https://openalex.org/W2992430691","https://openalex.org/W3001197829","https://openalex.org/W3005285208","https://openalex.org/W3016001968","https://openalex.org/W3032691658","https://openalex.org/W3035207996","https://openalex.org/W3047799303","https://openalex.org/W3096828317","https://openalex.org/W3120217483","https://openalex.org/W3173991475","https://openalex.org/W3199956316","https://openalex.org/W3204868648","https://openalex.org/W3208785409","https://openalex.org/W4206128876","https://openalex.org/W4285157298","https://openalex.org/W4285247267","https://openalex.org/W4289670464","https://openalex.org/W4293193531","https://openalex.org/W4298007608","https://openalex.org/W4384080275","https://openalex.org/W4386809042"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Multimodal":[0],"tasks":[1],"require":[2],"learning":[3,14,116,151,179],"a":[4,16,21,101],"joint":[5,17],"representation":[6,18],"of":[7,11,112,125,168],"the":[8,37,52,62,65,68,92,95,98,110,123,144,165,173,177],"constituent":[9],"modalities":[10],"data.":[12],"Contrastive":[13],"learns":[15],"by":[19],"using":[20,133],"contrastive":[22,115,150,178],"loss.":[23],"For":[24],"example,":[25],"CLIP":[26],"takes":[27],"as":[28],"input":[29],"image-caption":[30,48,56],"pairs":[31],"and":[32,42,85,97,106,120,139,186],"is":[33,103],"trained":[34],"to":[35],"maximize":[36],"similarity":[38,53],"between":[39,94],"an":[40],"image":[41,96],"its":[43],"corresponding":[44],"caption":[45,66],"in":[46,100,147,183],"actual":[47],"pairs,":[49],"while":[50],"minimizing":[51],"for":[54,79,164],"arbitrary":[55],"pairs.":[57],"This":[58],"approach":[59],"operates":[60],"on":[61,122],"premise":[63],"that":[64,81,91,142,176],"depicts":[67],"image's":[69],"content.":[70],"However,":[71],"this":[72],"assumption":[73],"does":[74],"not":[75],"always":[76],"hold":[77],"true":[78],"tweets":[80],"contain":[82],"both":[83],"text":[84,99],"images.":[86],"Previous":[87],"studies":[88],"have":[89],"indicated":[90],"connection":[93],"tweet":[102],"more":[104],"intricate":[105,145],"complex.":[107],"We":[108],"study":[109],"effectiveness":[111],"pre-trained":[113,149],"multimodal":[114,127,166],"models,":[117],"specifically,":[118],"CLIP,":[119],"ALIGN,":[121],"task":[124],"classifying":[126],"crisis":[128,169],"related":[129,170],"tweets.":[130,171],"Our":[131],"experiments":[132,174],"two":[134],"publicly":[135],"available":[136],"datasets,":[137],"CrisisMMD":[138],"DMD,":[140],"show":[141,175],"despite":[143],"relationships":[146],"tweets,":[148],"models":[152,180],"fine-tuned":[153],"with":[154],"task-specific":[155],"data":[156],"produce":[157],"better":[158],"results":[159],"than":[160],"prior":[161],"approaches":[162],"used":[163],"classification":[167],"Additionally,":[172],"are":[181],"effective":[182],"low-data":[184],"few-shot":[185],"cross-domain":[187],"settings.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-10T08:33:47.465468","created_date":"2025-10-10T00:00:00"}