{"id":"https://openalex.org/W4226174029","doi":"https://doi.org/10.1145/3486622.3493960","title":"On the Impact of Dataset Size:A Twitter Classification Case Study","display_name":"On the Impact of Dataset Size:A Twitter Classification Case Study","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4226174029","doi":"https://doi.org/10.1145/3486622.3493960"},"language":"en","primary_location":{"id":"doi:10.1145/3486622.3493960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3486622.3493960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.repo.uni-hannover.de/handle/123456789/15697","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047288191","display_name":"Thi Huyen Tram Nguyen","orcid":"https://orcid.org/0000-0001-8195-716X"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thi Huyen Nguyen","raw_affiliation_strings":["L3S Research Center, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049381739","display_name":"Hoang H. Nguyen","orcid":"https://orcid.org/0000-0003-0611-4634"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hoang H. Nguyen","raw_affiliation_strings":["L3S Research Center, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035434415","display_name":"Zahra Ahmadi","orcid":"https://orcid.org/0000-0003-1110-4756"},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zahra Ahmadi","raw_affiliation_strings":["L3S Research Center, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005512421","display_name":"Tuan-Anh Hoang","orcid":"https://orcid.org/0000-0003-3892-4762"},"institutions":[{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tuan-Anh Hoang","raw_affiliation_strings":["VNU University of Science, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNU University of Science, Vietnam","institution_ids":["https://openalex.org/I67868205"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110515510","display_name":"Thanh-Nam Doan","orcid":null},"institutions":[{"id":"https://openalex.org/I177097968","display_name":"University of Tennessee at Chattanooga","ror":"https://ror.org/00nqb1v70","country_code":"US","type":"education","lineage":["https://openalex.org/I177097968"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thanh-Nam Doan","raw_affiliation_strings":["University of Tennessee at Chattanooga, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee at Chattanooga, USA","institution_ids":["https://openalex.org/I177097968"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2798,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66595204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"210","last_page":"217"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8052732348442078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7002272009849548},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6956373453140259},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5740795135498047},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5570465326309204},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5442339777946472},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5105172395706177},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.48189860582351685},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.46644896268844604},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.46249982714653015},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4369755983352661},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4269309341907501},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25483405590057373},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16460782289505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8052732348442078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7002272009849548},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6956373453140259},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5740795135498047},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5570465326309204},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5442339777946472},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5105172395706177},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.48189860582351685},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.46644896268844604},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.46249982714653015},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4369755983352661},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4269309341907501},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25483405590057373},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16460782289505005},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3486622.3493960","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3486622.3493960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:www.repo.uni-hannover.de:123456789/15697","is_oa":true,"landing_page_url":"https://www.repo.uni-hannover.de/handle/123456789/15697","pdf_url":null,"source":{"id":"https://openalex.org/S4306401575","display_name":"Institutional Repository of Leibniz Universit\u00e4t Hannover (Leibniz Universit\u00e4t Hannover)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114112103","host_organization_name":"Leibniz University Hannover","host_organization_lineage":["https://openalex.org/I114112103"],"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":"IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"doi:10.15488/15576","is_oa":true,"landing_page_url":"https://doi.org/10.15488/15576","pdf_url":null,"source":{"id":"https://openalex.org/S7407052956","display_name":"Leibniz Universit\u00e4t Hannover","issn_l":null,"issn":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:www.repo.uni-hannover.de:123456789/15697","is_oa":true,"landing_page_url":"https://www.repo.uni-hannover.de/handle/123456789/15697","pdf_url":null,"source":{"id":"https://openalex.org/S4306401575","display_name":"Institutional Repository of Leibniz Universit\u00e4t Hannover (Leibniz Universit\u00e4t Hannover)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114112103","host_organization_name":"Leibniz University Hannover","host_organization_lineage":["https://openalex.org/I114112103"],"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":"IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2364254700","display_name":"Real time network, text, and speaker analytics for combating organized crime","funder_award_id":"833635","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6855405882","display_name":"Migration-Related Risks caused by misconceptions of Opportunities and Requirement","funder_award_id":"832921","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494547740","https://openalex.org/W1689711448","https://openalex.org/W1924689489","https://openalex.org/W2008056655","https://openalex.org/W2016944307","https://openalex.org/W2021097538","https://openalex.org/W2066946967","https://openalex.org/W2124499489","https://openalex.org/W2132886902","https://openalex.org/W2251009596","https://openalex.org/W2793109577","https://openalex.org/W2798575764","https://openalex.org/W2888501547","https://openalex.org/W2919587621","https://openalex.org/W2944338799","https://openalex.org/W2953558204","https://openalex.org/W2982300823","https://openalex.org/W3099342932","https://openalex.org/W3104186312"],"related_works":["https://openalex.org/W1586607209","https://openalex.org/W122912556","https://openalex.org/W4312414840","https://openalex.org/W2621411691","https://openalex.org/W2271357838","https://openalex.org/W2556866732","https://openalex.org/W2328989934","https://openalex.org/W2348322200","https://openalex.org/W2981952041","https://openalex.org/W3148060700"],"abstract_inverted_index":{"The":[0],"recent":[1,162,185],"advent":[2],"and":[3,9,59,73,102,152,207],"evolution":[4],"of":[5,32,77,87,116,133,140,176,197],"deep":[6,163],"learning":[7,89,135,164,171],"models":[8,136,165,187],"pre-trained":[10,186],"embedding":[11],"techniques":[12],"have":[13,188],"created":[14],"a":[15,63,88,92,100,124,194],"breakthrough":[16],"in":[17,84,113,173,216],"supervised":[18,33,134,217],"learning.":[19,218],"Typically,":[20],"we":[21,108,156],"expect":[22],"that":[23],"adding":[24,204,209],"more":[25,40,201,205,210],"labeled":[26,41],"data":[27,42,57,141,178,191,211],"improves":[28],"the":[29,36,67,74,85,96,114,130,138,161,174],"predictive":[30],"performance":[31,76,131],"models.":[34],"On":[35],"other":[37],"hand,":[38],"collecting":[39],"is":[43,212],"not":[44,213],"an":[45],"easy":[46],"task":[47],"due":[48],"to":[49,127,168],"several":[50],"difficulties,":[51],"such":[52,99],"as":[53],"manual":[54],"labor":[55],"costs,":[56],"privacy,":[58],"computational":[60],"constraint.":[61],"Hence,":[62],"comprehensive":[64],"study":[65,157],"on":[66,110,143],"relation":[68],"between":[69],"training":[70],"set":[71],"size":[72],"classification":[75],"different":[78],"methods":[79],"could":[80],"be":[81],"essentially":[82],"useful":[83],"selection":[86],"model":[90],"for":[91],"specific":[93],"task.":[94],"However,":[95],"literature":[97],"lacks":[98],"thorough":[101],"systematic":[103,125],"study.":[104],"In":[105],"this":[106,111],"paper,":[107],"concentrate":[109],"relationship":[112],"context":[115],"short,":[117],"noisy":[118],"texts":[119],"from":[120],"Twitter.":[121],"We":[122],"design":[123],"mechanism":[126],"comprehensively":[128],"observe":[129],"improvement":[132],"with":[137],"increase":[139],"sizes":[142],"three":[144],"well-known":[145],"Twitter":[146],"tasks:":[147],"sentiment":[148],"analysis,":[149],"informativeness":[150],"detection,":[151],"information":[153],"relevance.":[154],"Besides,":[155],"how":[158],"significantly":[159],"better":[160],"are":[166],"compared":[167],"traditional":[169],"machine":[170],"approaches":[172],"case":[175],"various":[177],"sizes.":[179],"Our":[180],"extensive":[181],"experiments":[182],"show":[183],"(a)":[184],"overcome":[189],"big":[190],"requirements,":[192],"(b)":[193],"good":[195],"choice":[196],"text":[198],"representation":[199],"has":[200],"impact":[202],"than":[203],"data,":[206],"(c)":[208],"always":[214],"beneficial":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}