{"id":"https://openalex.org/W4406264418","doi":"https://doi.org/10.1109/icset63729.2024.10775292","title":"Enhancing Social Media Accessibility: Automatic Alternative Text Generation in X by Image Captioning","display_name":"Enhancing Social Media Accessibility: Automatic Alternative Text Generation in X by Image Captioning","publication_year":2024,"publication_date":"2024-10-02","ids":{"openalex":"https://openalex.org/W4406264418","doi":"https://doi.org/10.1109/icset63729.2024.10775292"},"language":"en","primary_location":{"id":"doi:10.1109/icset63729.2024.10775292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icset63729.2024.10775292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 14th International Conference on System Engineering and Technology (ICSET)","raw_type":"proceedings-article"},"type":"article","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/A5093133772","display_name":"Jessica Lynn Wibowo","orcid":null},"institutions":[{"id":"https://openalex.org/I166073570","display_name":"Binus University","ror":"https://ror.org/03zmf4s77","country_code":"ID","type":"education","lineage":["https://openalex.org/I166073570"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Jessica Lynn Wibowo","raw_affiliation_strings":["Bina Nusantara University,School of Computer Science,Computer Science Department,Jakarta,Indonesia,11480"],"affiliations":[{"raw_affiliation_string":"Bina Nusantara University,School of Computer Science,Computer Science Department,Jakarta,Indonesia,11480","institution_ids":["https://openalex.org/I166073570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108774861","display_name":"G Gunawan","orcid":"https://orcid.org/0000-0002-4141-7465"},"institutions":[{"id":"https://openalex.org/I166073570","display_name":"Binus University","ror":"https://ror.org/03zmf4s77","country_code":"ID","type":"education","lineage":["https://openalex.org/I166073570"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Gabriel Seemore Gunawan","raw_affiliation_strings":["Bina Nusantara University,School of Computer Science,Computer Science Department,Jakarta,Indonesia,11480"],"affiliations":[{"raw_affiliation_string":"Bina Nusantara University,School of Computer Science,Computer Science Department,Jakarta,Indonesia,11480","institution_ids":["https://openalex.org/I166073570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041783188","display_name":"Ivan Sebastian Edbert","orcid":"https://orcid.org/0000-0001-8484-5008"},"institutions":[{"id":"https://openalex.org/I166073570","display_name":"Binus University","ror":"https://ror.org/03zmf4s77","country_code":"ID","type":"education","lineage":["https://openalex.org/I166073570"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ivan Sebastian Edbert","raw_affiliation_strings":["Bina Nusantara University,School of Computer Science,Computer Science Department,Jakarta,Indonesia,11480"],"affiliations":[{"raw_affiliation_string":"Bina Nusantara University,School of Computer Science,Computer Science Department,Jakarta,Indonesia,11480","institution_ids":["https://openalex.org/I166073570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093133772"],"corresponding_institution_ids":["https://openalex.org/I166073570"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58653247,"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":"123","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9937000274658203,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9937000274658203,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.972599983215332,"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/T10028","display_name":"Topic Modeling","score":0.9542999863624573,"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/closed-captioning","display_name":"Closed captioning","score":0.9531629085540771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6681790351867676},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.603898286819458},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.544002115726471},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43616536259651184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42379963397979736},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.382021427154541},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35064762830734253},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3360050320625305},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27739670872688293}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9531629085540771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6681790351867676},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.603898286819458},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.544002115726471},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43616536259651184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42379963397979736},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.382021427154541},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35064762830734253},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3360050320625305},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27739670872688293}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icset63729.2024.10775292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icset63729.2024.10775292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 14th International Conference on System Engineering and Technology (ICSET)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"In":[0],"the":[1,60,64,75,78,86,117,128,144,166],"contemporary":[2],"digital":[3,150],"landscape,":[4],"social":[5,34,124,167],"media\u2019s":[6],"reliance":[7],"on":[8,33,43,74],"visual":[9,18],"content":[10],"poses":[11],"significant":[12],"accessibility":[13,32,111,139],"barriers":[14],"for":[15,41,112],"individuals":[16],"with":[17,59],"impairments,":[19],"sidelining":[20],"a":[21],"substantial":[22],"user":[23],"base.":[24],"This":[25,141],"study":[26],"applies":[27],"Artificial":[28],"Intelligence":[29],"to":[30,101,148],"improve":[31],"media":[35,125,168],"by":[36,92],"automating":[37],"alternative":[38],"text":[39],"generation":[40],"images":[42],"platform":[44],"X":[45],"(formerly":[46],"Twitter).":[47],"The":[48,95],"Generative":[49],"Image-to-text":[50],"Transformer":[51],"(GIT)":[52],"model":[53,79,89],"is":[54],"analyzed":[55],"and":[56,69,104,156],"then":[57],"integrated":[58],"Twitter":[61],"API.":[62],"Using":[63],"Flickr30k":[65],"dataset,":[66],"further":[67],"fine-tuning":[68],"evaluation":[70],"processes":[71],"are":[72],"performed":[73],"model.":[76],"Concurrently,":[77],"demonstrates":[80],"higher":[81],"accuracy":[82],"of":[83,119,131,146],"106%":[84],"over":[85],"baseline":[87],"VGG":[88],"as":[90],"quantified":[91],"ROUGE":[93],"metrics.":[94],"results":[96],"confirm":[97],"our":[98],"model\u2019s":[99],"capability":[100],"produce":[102],"descriptive":[103],"contextually":[105],"relevant":[106],"captions":[107],"that":[108,158],"significantly":[109],"enhance":[110],"visually":[113,159],"impaired":[114,160],"users.":[115],"Furthermore,":[116],"integration":[118],"this":[120],"AI-driven":[121],"solution":[122],"into":[123],"platforms":[126],"showcases":[127],"practical":[129],"application":[130],"advanced":[132],"machine":[133],"learning":[134],"techniques":[135],"in":[136,165],"addressing":[137],"real-world":[138],"challenges.":[140],"research":[142],"highlights":[143],"potential":[145],"AI":[147],"transform":[149],"communication,":[151],"making":[152],"it":[153],"more":[154],"inclusive":[155],"ensuring":[157],"users":[161],"can":[162],"fully":[163],"participate":[164],"experience.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
