{"id":"https://openalex.org/W2921227513","doi":"https://doi.org/10.1145/3299819.3299836","title":"Do We Need More Training Samples For Text Classification?","display_name":"Do We Need More Training Samples For Text Classification?","publication_year":2018,"publication_date":"2018-12-21","ids":{"openalex":"https://openalex.org/W2921227513","doi":"https://doi.org/10.1145/3299819.3299836","mag":"2921227513"},"language":"en","primary_location":{"id":"doi:10.1145/3299819.3299836","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3299819.3299836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Artificial Intelligence and Cloud Computing Conference","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/A5100611610","display_name":"Wanwan Zheng","orcid":"https://orcid.org/0000-0003-4689-6044"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Wanwan Zheng","raw_affiliation_strings":["Doshisha University, Japan"],"affiliations":[{"raw_affiliation_string":"Doshisha University, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046812287","display_name":"Mingzhe Jin","orcid":"https://orcid.org/0000-0002-6012-1379"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mingzhe Jin","raw_affiliation_strings":["Doshisha University, Japan"],"affiliations":[{"raw_affiliation_string":"Doshisha University, Japan","institution_ids":["https://openalex.org/I133984924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100611610"],"corresponding_institution_ids":["https://openalex.org/I133984924"],"apc_list":null,"apc_paid":null,"fwci":0.3258,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69771499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9987999796867371,"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":0.9987999796867371,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9970999956130981,"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/T10057","display_name":"Face and Expression Recognition","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.9783799648284912},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7607841491699219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7556228637695312},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7342397570610046},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6857515573501587},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5851560235023499},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5558376312255859},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5552541017532349},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4875294864177704},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4253655672073364},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4192360043525696},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34530532360076904},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14158770442008972},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10758247971534729}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9783799648284912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7607841491699219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7556228637695312},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7342397570610046},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6857515573501587},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5851560235023499},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5558376312255859},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5552541017532349},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4875294864177704},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4253655672073364},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4192360043525696},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34530532360076904},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14158770442008972},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10758247971534729},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3299819.3299836","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3299819.3299836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 Artificial Intelligence and Cloud Computing Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1540596182","https://openalex.org/W1560006303","https://openalex.org/W1839863673","https://openalex.org/W1999404243","https://openalex.org/W2008056655","https://openalex.org/W2082874195","https://openalex.org/W2099741732","https://openalex.org/W2100235759","https://openalex.org/W2103018059","https://openalex.org/W2106525823","https://openalex.org/W2112341432","https://openalex.org/W2117170950","https://openalex.org/W2124706543","https://openalex.org/W2129476886","https://openalex.org/W2149407554","https://openalex.org/W2156665896","https://openalex.org/W2167101736","https://openalex.org/W2169103656","https://openalex.org/W2294798173","https://openalex.org/W2435251607","https://openalex.org/W2490800645","https://openalex.org/W2744790735","https://openalex.org/W2766438525","https://openalex.org/W2781520366","https://openalex.org/W2803393527","https://openalex.org/W2914499414","https://openalex.org/W2998768810","https://openalex.org/W3023786531","https://openalex.org/W3085162807","https://openalex.org/W3125817276"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W4295122168","https://openalex.org/W3155717344","https://openalex.org/W1770458422","https://openalex.org/W4386564352","https://openalex.org/W2952668426","https://openalex.org/W4312531262","https://openalex.org/W4388103534","https://openalex.org/W4318142952","https://openalex.org/W2072070946"],"abstract_inverted_index":{"In":[0,22,105],"recent":[1],"years,":[2],"with":[3],"the":[4,23,36,119,122,129,143],"rise":[5],"of":[6,25,33,93,121,125,136],"exceptional":[7],"cloud":[8],"computing":[9],"technologies,":[10],"machine":[11,28,61,72],"learning":[12,29,73],"approach":[13],"in":[14,56,71,81],"solving":[15],"complex":[16],"problems":[17],"has":[18],"been":[19],"greatly":[20],"accelerated.":[21],"field":[24],"text":[26],"classification,":[27],"is":[30,49,77,110],"a":[31,60,90,133,149,163],"technology":[32,150],"providing":[34],"computers":[35],"ability":[37],"to":[38,58,62,68,88,112,115,151,159,162],"learn":[39],"and":[40,47,75],"predict":[41],"tasks":[42],"without":[43],"being":[44],"explicitly":[45],"labeled,":[46],"it":[48],"said":[50],"that":[51],"enough":[52],"data":[53,66],"are":[54,86],"needed":[55],"order":[57],"let":[59],"learn.":[63],"However,":[64],"more":[65],"tend":[67],"cause":[69],"overfitting":[70,161],"algorithms,":[74],"there":[76],"no":[78],"object":[79],"criteria":[80],"deciding":[82],"how":[83],"many":[84],"samples":[85],"required":[87,123],"achieve":[89],"desired":[91],"level":[92],"performance.":[94],"This":[95],"article":[96],"addresses":[97],"this":[98],"problem":[99],"by":[100],"using":[101],"feature":[102,108,146],"selection":[103,109,147],"method.":[104],"our":[106],"experiments,":[107],"proved":[111],"be":[113,157],"able":[114,158],"decrease":[116],"66.67%":[117],"at":[118,142],"largest":[120],"size":[124],"training":[126],"dataset.":[127],"Meanwhile,":[128],"kappa":[130],"coefficient":[131],"as":[132,148],"performance":[134],"measure":[135],"classifiers":[137],"could":[138],"increase":[139],"11":[140],"points":[141],"maximum.":[144],"Furthermore,":[145],"remove":[152],"irrelevant":[153],"features":[154],"was":[155],"found":[156],"prevent":[160],"great":[164],"extent.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}