{"id":"https://openalex.org/W7126413743","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.76","title":"Improving Multimodal Classification of Social Media Posts by Leveraging Image-Text Auxiliary Tasks","display_name":"Improving Multimodal Classification of Social Media Posts by Leveraging Image-Text Auxiliary Tasks","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126413743","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.76"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.76","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.76","pdf_url":"https://aclanthology.org/2024.findings-eacl.76.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.76.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087779117","display_name":"Danae S\u00e1nchez Villegas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danae Sanchez Villegas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124632830","display_name":"Daniel Preotiuc-Pietro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Preotiuc-Pietro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124495639","display_name":"Nikolaos Aletras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Aletras","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70260521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1126","last_page":"1137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.2222999930381775,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.2222999930381775,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.13850000500679016,"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/T11644","display_name":"Spam and Phishing Detection","score":0.051100000739097595,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/social-media","display_name":"Social media","score":0.6021999716758728},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.31779998540878296},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.28619998693466187},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.26589998602867126},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.25920000672340393},{"id":"https://openalex.org/keywords/legibility","display_name":"Legibility","score":0.25870001316070557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6409000158309937},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6021999716758728},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38850000500679016},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34220001101493835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3237000107765198},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2888000011444092},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C2779332521","wikidata":"https://www.wikidata.org/wiki/Q1820694","display_name":"Legibility","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.76","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.76","pdf_url":"https://aclanthology.org/2024.findings-eacl.76.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.76","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.76","pdf_url":"https://aclanthology.org/2024.findings-eacl.76.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2831959038","display_name":null,"funder_award_id":"EP/S023062","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"},{"id":"https://openalex.org/G5306878388","display_name":null,"funder_award_id":"EP/S023062/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320319993","display_name":"Leverhulme Trust","ror":"https://ror.org/012mzw131"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126413743.pdf","grobid_xml":"https://content.openalex.org/works/W7126413743.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Effectively":[0],"leveraging":[1],"multimodal":[2,48,82,150],"information":[3],"from":[4],"social":[5,51,155],"media":[6,52,156],"posts":[7,53,105],"is":[8,28,43,87,177],"essential":[9],"to":[10,89,125,138,163],"various":[11],"downstream":[12],"tasks":[13],"such":[14],"as":[15],"sentiment":[16],"analysis,":[17],"sarcasm":[18],"detection":[19],"or":[20,36,141],"hate":[21],"speech":[22],"classification.Jointly":[23],"modeling":[24],"text":[25,42],"and":[26,41,132],"images":[27,131],"challenging":[29],"because":[30],"cross-modal":[31],"semantics":[32],"might":[33],"be":[34],"hidden":[35],"the":[37,68,77,91,102,107,115,122,127,170],"relation":[38],"between":[39,93,104,130],"image":[40,108],"weak.However,":[44],"prior":[45],"work":[46],"on":[47,67],"classification":[49],"of":[50,70,161],"has":[54],"not":[55],"yet":[56],"addressed":[57],"these":[58,146],"challenges.In":[59],"this":[60],"work,":[61],"we":[62],"present":[63],"an":[64,110],"extensive":[65],"study":[66],"effectiveness":[69],"using":[71],"two":[72],"auxiliary":[73,175],"losses":[74],"jointly":[75],"with":[76,148],"main":[78],"task":[79,176],"during":[80],"fine-tuning":[81],"models.First,":[83],"Image-Text":[84,118],"Contrastive":[85],"(ITC)":[86],"designed":[88],"minimize":[90],"distance":[92],"imagetext":[94],"representations":[95],"within":[96],"a":[97],"post,":[98],"thereby":[99],"effectively":[100],"bridging":[101],"gap":[103],"where":[106,173],"plays":[109],"important":[111],"role":[112],"in":[113],"conveying":[114],"post's":[116],"meaning.Second,":[117],"Matching":[119],"(ITM)":[120],"enhances":[121],"model's":[123],"ability":[124],"understand":[126],"semantic":[128],"relationship":[129],"text,":[133],"thus":[134],"improving":[135],"its":[136],"capacity":[137],"handle":[139],"ambiguous":[140],"loosely":[142],"related":[143],"modalities.We":[144],"combine":[145],"objectives":[147],"five":[149,153],"models":[151],"across":[152],"diverse":[154],"datasets,":[157],"demonstrating":[158],"consistent":[159],"improvements":[160],"up":[162],"2.6":[164],"F1":[165],"score.Our":[166],"comprehensive":[167],"analysis":[168],"shows":[169],"specific":[171],"scenarios":[172],"each":[174],"most":[178],"effective.":[179],"1":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}