{"id":"https://openalex.org/W4361004466","doi":"https://doi.org/10.3390/bdcc7020061","title":"A Mixed Malay\u2013English Language COVID-19 Twitter Dataset: A Sentiment Analysis","display_name":"A Mixed Malay\u2013English Language COVID-19 Twitter Dataset: A Sentiment Analysis","publication_year":2023,"publication_date":"2023-03-27","ids":{"openalex":"https://openalex.org/W4361004466","doi":"https://doi.org/10.3390/bdcc7020061"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc7020061","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc7020061","pdf_url":"https://www.mdpi.com/2504-2289/7/2/61/pdf?version=1679903638","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/7/2/61/pdf?version=1679903638","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032579914","display_name":"Jeffery T. H. Kong","orcid":"https://orcid.org/0000-0001-7453-5532"},"institutions":[{"id":"https://openalex.org/I158949172","display_name":"Curtin University Sarawak","ror":"https://ror.org/024fm2y42","country_code":"MY","type":"education","lineage":["https://openalex.org/I158949172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Jeffery T. H. Kong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Curtin University Malaysia, Miri 98009, Malaysia"],"raw_orcid":"https://orcid.org/0000-0001-7453-5532","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Curtin University Malaysia, Miri 98009, Malaysia","institution_ids":["https://openalex.org/I158949172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048813856","display_name":"Filbert H. Juwono","orcid":"https://orcid.org/0000-0002-2596-8101"},"institutions":[{"id":"https://openalex.org/I4210139412","display_name":"University of Southampton Malaysia","ror":"https://ror.org/04vxw9c34","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210139412","https://openalex.org/I43439940"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Filbert H. Juwono","raw_affiliation_strings":["Computer Science Program, University of Southampton Malaysia, Iskandar Puteri 79100, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Program, University of Southampton Malaysia, Iskandar Puteri 79100, Malaysia","institution_ids":["https://openalex.org/I4210139412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046819369","display_name":"Ik Ying Ngu","orcid":null},"institutions":[{"id":"https://openalex.org/I158949172","display_name":"Curtin University Sarawak","ror":"https://ror.org/024fm2y42","country_code":"MY","type":"education","lineage":["https://openalex.org/I158949172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ik Ying Ngu","raw_affiliation_strings":["Department of Media and Communication, Curtin University Malaysia, Miri 98009, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Media and Communication, Curtin University Malaysia, Miri 98009, Malaysia","institution_ids":["https://openalex.org/I158949172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083725495","display_name":"I Gde Dharma Nugraha","orcid":"https://orcid.org/0000-0002-4960-7968"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"I. Gde Dharma Nugraha","raw_affiliation_strings":["Department of Electrical Engineering, Universitas Indonesia, Depok 16424, Indonesia"],"raw_orcid":"https://orcid.org/0000-0002-4960-7968","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Universitas Indonesia, Depok 16424, Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008782052","display_name":"Yan Maraden","orcid":"https://orcid.org/0000-0002-6737-7115"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Yan Maraden","raw_affiliation_strings":["Department of Electrical Engineering, Universitas Indonesia, Depok 16424, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Universitas Indonesia, Depok 16424, Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012079120","display_name":"W. K. Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139412","display_name":"University of Southampton Malaysia","ror":"https://ror.org/04vxw9c34","country_code":"MY","type":"education","lineage":["https://openalex.org/I4210139412","https://openalex.org/I43439940"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"W. K. Wong","raw_affiliation_strings":["Computer Science Program, University of Southampton Malaysia, Iskandar Puteri 79100, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Program, University of Southampton Malaysia, Iskandar Puteri 79100, Malaysia","institution_ids":["https://openalex.org/I4210139412"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083725495"],"corresponding_institution_ids":["https://openalex.org/I29617571"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":1.6911,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.85731453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":"2","first_page":"61","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9998000264167786,"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":0.9998000264167786,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9926000237464905,"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":0.7617860436439514},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.7006646394729614},{"id":"https://openalex.org/keywords/malay","display_name":"Malay","score":0.6784615516662598},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6181412935256958},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.6169155240058899},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6062808036804199},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6021597981452942},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5520015954971313},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43441492319107056},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4250059425830841},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32348281145095825},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26853662729263306},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1848749816417694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617860436439514},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.7006646394729614},{"id":"https://openalex.org/C2776938241","wikidata":"https://www.wikidata.org/wiki/Q9237","display_name":"Malay","level":2,"score":0.6784615516662598},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6181412935256958},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.6169155240058899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6062808036804199},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6021597981452942},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5520015954971313},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43441492319107056},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4250059425830841},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32348281145095825},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26853662729263306},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1848749816417694},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/bdcc7020061","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc7020061","pdf_url":"https://www.mdpi.com/2504-2289/7/2/61/pdf?version=1679903638","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:espace.curtin.edu.au:20.500.11937/95202","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11937/95202","pdf_url":"https://espace.curtin.edu.au/bitstream/20.500.11937/95202/2/94986.pdf","source":{"id":"https://openalex.org/S4306401790","display_name":"eSpace (Curtin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205640436","host_organization_name":"Curtin University","host_organization_lineage":["https://openalex.org/I205640436"],"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":"Journal Article"},{"id":"pmh:oai:doaj.org/article:f5b6bcef53634eff9a38497056204b8c","is_oa":true,"landing_page_url":"https://doaj.org/article/f5b6bcef53634eff9a38497056204b8c","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 7, Iss 2, p 61 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2504-2289/7/2/61/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/bdcc7020061","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Big Data and Cognitive Computing; Volume 7; Issue 2; Pages: 61","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/bdcc7020061","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc7020061","pdf_url":"https://www.mdpi.com/2504-2289/7/2/61/pdf?version=1679903638","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.800000011920929,"id":"https://metadata.un.org/sdg/3"}],"awards":[{"id":"https://openalex.org/G1524716514","display_name":null,"funder_award_id":"RST/HKP.05.00/2020","funder_id":"https://openalex.org/F4320323819","funder_display_name":"Universitas Indonesia"},{"id":"https://openalex.org/G2042605105","display_name":null,"funder_award_id":"NKB-1409/UN2.RST/HKP.05.00/2020","funder_id":"https://openalex.org/F4320321709","funder_display_name":"Ministry of Higher Education, Malaysia"},{"id":"https://openalex.org/G2734029420","display_name":null,"funder_award_id":"FRGS/1/2020/ICT06/CURTIN/02/1","funder_id":"https://openalex.org/F4320321709","funder_display_name":"Ministry of Higher Education, Malaysia"},{"id":"https://openalex.org/G5077554664","display_name":null,"funder_award_id":"NKB-1409/UN2.RST/HKP.05.00/2020","funder_id":"https://openalex.org/F4320323819","funder_display_name":"Universitas Indonesia"},{"id":"https://openalex.org/G5864509922","display_name":null,"funder_award_id":"FRGS/1/2020/ICT06/CURTIN/02/1","funder_id":"https://openalex.org/F4320323819","funder_display_name":"Universitas Indonesia"},{"id":"https://openalex.org/G7379709468","display_name":null,"funder_award_id":"00/2020","funder_id":"https://openalex.org/F4320323819","funder_display_name":"Universitas Indonesia"}],"funders":[{"id":"https://openalex.org/F4320320987","display_name":"Curtin University of Technology","ror":"https://ror.org/02n415q13"},{"id":"https://openalex.org/F4320321709","display_name":"Ministry of Higher Education, Malaysia","ror":"https://ror.org/05mcs2t73"},{"id":"https://openalex.org/F4320323819","display_name":"Universitas Indonesia","ror":"https://ror.org/0116zj450"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4361004466.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W2019764219","https://openalex.org/W2149164606","https://openalex.org/W2511558409","https://openalex.org/W2588299583","https://openalex.org/W2792883466","https://openalex.org/W2801599720","https://openalex.org/W2891488835","https://openalex.org/W2896457183","https://openalex.org/W2900908259","https://openalex.org/W2900946789","https://openalex.org/W2911295418","https://openalex.org/W2912094972","https://openalex.org/W2952638691","https://openalex.org/W2954291758","https://openalex.org/W2954341730","https://openalex.org/W2973887018","https://openalex.org/W3001420715","https://openalex.org/W3011711616","https://openalex.org/W3019581400","https://openalex.org/W3025940698","https://openalex.org/W3047061478","https://openalex.org/W3087682989","https://openalex.org/W3089809702","https://openalex.org/W3097181570","https://openalex.org/W3103182178","https://openalex.org/W3125474344","https://openalex.org/W3155397102","https://openalex.org/W3155743827","https://openalex.org/W3160009589","https://openalex.org/W3163282782","https://openalex.org/W3167664986","https://openalex.org/W3185166685","https://openalex.org/W3195681467","https://openalex.org/W3201846888","https://openalex.org/W3210570880","https://openalex.org/W3212179987","https://openalex.org/W3214048859","https://openalex.org/W4200044348","https://openalex.org/W4200490163","https://openalex.org/W4210654372","https://openalex.org/W4214747394","https://openalex.org/W6601894380","https://openalex.org/W6748411227","https://openalex.org/W6758620931","https://openalex.org/W6763687114","https://openalex.org/W6783431809"],"related_works":["https://openalex.org/W3079964180","https://openalex.org/W2328052390","https://openalex.org/W375642441","https://openalex.org/W2288251828","https://openalex.org/W3044024082","https://openalex.org/W3158961892","https://openalex.org/W4235312256","https://openalex.org/W4387772941","https://openalex.org/W4386885143","https://openalex.org/W4387272222"],"abstract_inverted_index":{"Social":[0],"media":[1,53],"has":[2,274],"evolved":[3],"into":[4,145,205,217],"a":[5,17,62,83,95,154,164],"platform":[6],"for":[7,47,187,241,277],"the":[8,23,27,79,140,173,182,210,214,237,254,264,270,275],"dissemination":[9],"of":[10,19,26,64,71,82,87,142],"information,":[11],"including":[12],"fake":[13],"news.":[14],"There":[15],"is":[16,197,243],"lot":[18],"false":[20,35],"information":[21,36],"about":[22],"current":[24],"situation":[25],"Coronavirus":[28],"Disease":[29],"2019":[30],"(COVID-19)":[31],"pandemic,":[32],"such":[33,54],"as":[34,55],"regarding":[37],"vaccination.":[38],"In":[39,111],"this":[40,88,160],"paper,":[41],"we":[42,93,113,162,212],"focus":[43],"on":[44,51,172],"sentiment":[45,141,156],"analysis":[46,157],"Malaysian":[48],"COVID-19-related":[49],"news":[50],"social":[52],"Twitter.":[56],"Tweets":[57],"in":[58,120,124,127,131],"Malaysia":[59],"are":[60,90],"often":[61],"combination":[63],"Malay,":[65],"English,":[66,125],"and":[67,76,129,138,150,175,190,202,230],"Chinese":[68],"with":[69,117,227],"plenty":[70],"short":[72],"forms,":[73],"symbols,":[74],"emojis,":[75],"emoticons":[77],"within":[78],"maximum":[80],"length":[81],"tweet.":[84],"The":[85,233],"contributions":[86],"paper":[89],"twofold.":[91],"Firstly,":[92],"built":[94],"multilingual":[96,279],"COVID-19":[97],"Twitter":[98],"dataset,":[99],"comprising":[100],"tweets":[101,144,216],"written":[102],"from":[103],"1":[104],"September":[105],"2021":[106],"to":[107,152,199,253],"12":[108],"December":[109],"2021.":[110],"particular,":[112],"collected":[114],"108,246":[115],"tweets,":[116],"over":[118],"67%":[119],"Malay":[121],"language,":[122],"27%":[123],"2%":[126],"Chinese,":[128],"4%":[130],"other":[132],"languages.":[133],"We":[134],"then":[135],"manually":[136],"annotated":[137],"assigned":[139],"11,568":[143],"three-class":[146],"sentiments":[147],"(positive,":[148],"negative,":[149],"neutral)":[151],"develop":[153],"Malay-language":[155],"tool.":[158],"For":[159],"purpose,":[161],"applied":[163],"data":[165],"compression":[166],"method":[167],"using":[168],"Byte-Pair":[169],"Encoding":[170],"(BPE)":[171],"texts":[174],"used":[176,198],"two":[177],"deep":[178],"learning":[179],"approaches,":[180],"i.e.,":[181],"Multilingual":[183],"Bidirectional":[184],"Encoder":[185],"Representation":[186],"Transformer":[188],"(M-BERT)":[189],"convolutional":[191],"neural":[192],"network":[193,273],"(CNN).":[194],"BPE":[195,224,242],"tokenization":[196],"encode":[200],"rare":[201],"unknown":[203],"words":[204],"smaller":[206],"meaningful":[207],"subwords.":[208],"With":[209],"CNN,":[211],"converted":[213],"labeled":[215],"image":[218],"files.":[219],"Our":[220],"experiments":[221],"explored":[222],"different":[223],"vocabulary":[225,239],"sizes":[226],"our":[228,257,278],"BPE-Text-to-Image-CNN":[229],"BPE-M-BERT":[231,261],"models.":[232],"results":[234,258],"show":[235,259],"that":[236,248,260,269],"optimal":[238],"size":[240],"12,000;":[244],"any":[245],"values":[246],"beyond":[247],"would":[249],"not":[250],"contribute":[251],"much":[252],"F1-score.":[255],"Overall,":[256],"slightly":[262],"outperforms":[263],"CNN":[265],"model,":[266],"thereby":[267],"showing":[268],"pre-trained":[271],"M-BERT":[272],"advantage":[276],"dataset.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2023-03-30T00:00:00"}
