{"id":"https://openalex.org/W4367627723","doi":"https://doi.org/10.3390/a16050236","title":"Twenty Years of Machine-Learning-Based Text Classification: A Systematic Review","display_name":"Twenty Years of Machine-Learning-Based Text Classification: A Systematic Review","publication_year":2023,"publication_date":"2023-04-29","ids":{"openalex":"https://openalex.org/W4367627723","doi":"https://doi.org/10.3390/a16050236"},"language":"en","primary_location":{"id":"doi:10.3390/a16050236","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a16050236","pdf_url":"https://www.mdpi.com/1999-4893/16/5/236/pdf?version=1683271657","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"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":"Algorithms","raw_type":"journal-article"},"type":"review","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/16/5/236/pdf?version=1683271657","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002183673","display_name":"Ashokkumar Palanivinayagam","orcid":null},"institutions":[{"id":"https://openalex.org/I20107917","display_name":"Sri Ramachandra Institute of Higher Education and Research","ror":"https://ror.org/0108gdg43","country_code":"IN","type":"education","lineage":["https://openalex.org/I20107917"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashokkumar Palanivinayagam","raw_affiliation_strings":["Sri Ramachandra Faculty of Engineering and Technology, Sri Ramachandra Institute of Higher Education and Research, Chennai 600116, India"],"affiliations":[{"raw_affiliation_string":"Sri Ramachandra Faculty of Engineering and Technology, Sri Ramachandra Institute of Higher Education and Research, Chennai 600116, India","institution_ids":["https://openalex.org/I20107917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058425001","display_name":"Claude Ziad El\u2010Bayeh","orcid":"https://orcid.org/0000-0002-8268-8878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Claude Ziad El-Bayeh","raw_affiliation_strings":["Department of Electrical Engineering, Bayeh Institute, Amchit 4307, Lebanon"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Bayeh Institute, Amchit 4307, Lebanon","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042653526","display_name":"Robertas Dama\u0161evi\u010dius","orcid":"https://orcid.org/0000-0001-9990-1084"},"institutions":[{"id":"https://openalex.org/I172574986","display_name":"Kaunas University of Technology","ror":"https://ror.org/01me6gb93","country_code":"LT","type":"education","lineage":["https://openalex.org/I172574986"]}],"countries":["LT"],"is_corresponding":true,"raw_author_name":"Robertas Dama\u0161evi\u010dius","raw_affiliation_strings":["Department of Software Engineering, Kaunas University of Technology, 44249 Kaunas, Lithuania"],"affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Kaunas University of Technology, 44249 Kaunas, Lithuania","institution_ids":["https://openalex.org/I172574986"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042653526"],"corresponding_institution_ids":["https://openalex.org/I172574986"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":13.0784,"has_fulltext":true,"cited_by_count":76,"citation_normalized_percentile":{"value":0.99141737,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"16","issue":"5","first_page":"236","last_page":"236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9987999796867371,"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/T13083","display_name":"Advanced Text Analysis Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8287674188613892},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7952742576599121},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7677905559539795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7162984609603882},{"id":"https://openalex.org/keywords/systematic-review","display_name":"Systematic review","score":0.6078091263771057},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5255802273750305},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.48721522092819214},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43841394782066345},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40505316853523254},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3718984127044678},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3673635721206665},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.08939042687416077}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8287674188613892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7952742576599121},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677905559539795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7162984609603882},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.6078091263771057},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5255802273750305},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.48721522092819214},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43841394782066345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40505316853523254},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3718984127044678},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3673635721206665},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.08939042687416077},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/a16050236","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a16050236","pdf_url":"https://www.mdpi.com/1999-4893/16/5/236/pdf?version=1683271657","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"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":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:16f42e4756144ffbad99e10d2686a9fa","is_oa":true,"landing_page_url":"https://doaj.org/article/16f42e4756144ffbad99e10d2686a9fa","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 16, Iss 5, p 236 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-4893/16/5/236/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/a16050236","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":"Algorithms; Volume 16; Issue 5; Pages: 236","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/a16050236","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a16050236","pdf_url":"https://www.mdpi.com/1999-4893/16/5/236/pdf?version=1683271657","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"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":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367627723.pdf"},"referenced_works_count":147,"referenced_works":["https://openalex.org/W1560851690","https://openalex.org/W1855811457","https://openalex.org/W1960685374","https://openalex.org/W1965961515","https://openalex.org/W1967314128","https://openalex.org/W1980229662","https://openalex.org/W1990392005","https://openalex.org/W1991199867","https://openalex.org/W1991605331","https://openalex.org/W1992492534","https://openalex.org/W1993108184","https://openalex.org/W2007627477","https://openalex.org/W2008638605","https://openalex.org/W2010543449","https://openalex.org/W2025679133","https://openalex.org/W2026607267","https://openalex.org/W2026872460","https://openalex.org/W2057455558","https://openalex.org/W2064580901","https://openalex.org/W2064587498","https://openalex.org/W2094643277","https://openalex.org/W2108564850","https://openalex.org/W2112119668","https://openalex.org/W2114048520","https://openalex.org/W2114080886","https://openalex.org/W2115477592","https://openalex.org/W2118020653","https://openalex.org/W2131744502","https://openalex.org/W2133726535","https://openalex.org/W2134090438","https://openalex.org/W2145252566","https://openalex.org/W2145955806","https://openalex.org/W2156465113","https://openalex.org/W2161374186","https://openalex.org/W2164810648","https://openalex.org/W2164967910","https://openalex.org/W2189255847","https://openalex.org/W2317515691","https://openalex.org/W2358897293","https://openalex.org/W2412830130","https://openalex.org/W2413329758","https://openalex.org/W2493916176","https://openalex.org/W2509798479","https://openalex.org/W2540977243","https://openalex.org/W2545410393","https://openalex.org/W2550568647","https://openalex.org/W2558223934","https://openalex.org/W2588482014","https://openalex.org/W2591102410","https://openalex.org/W2591922431","https://openalex.org/W2595321735","https://openalex.org/W2597485909","https://openalex.org/W2603530161","https://openalex.org/W2611929813","https://openalex.org/W2729098382","https://openalex.org/W2742408064","https://openalex.org/W2751437889","https://openalex.org/W2759968762","https://openalex.org/W2795300694","https://openalex.org/W2800649250","https://openalex.org/W2802787326","https://openalex.org/W2803237632","https://openalex.org/W2884503196","https://openalex.org/W2891768540","https://openalex.org/W2898339904","https://openalex.org/W2900743892","https://openalex.org/W2908092214","https://openalex.org/W2913351023","https://openalex.org/W2919466488","https://openalex.org/W2922081354","https://openalex.org/W2934798344","https://openalex.org/W2937423263","https://openalex.org/W2943038294","https://openalex.org/W2951603891","https://openalex.org/W2962739339","https://openalex.org/W2962839482","https://openalex.org/W2963910295","https://openalex.org/W2967475656","https://openalex.org/W2972351145","https://openalex.org/W2972715831","https://openalex.org/W2974335209","https://openalex.org/W2976395159","https://openalex.org/W2977542692","https://openalex.org/W2980525811","https://openalex.org/W3007497615","https://openalex.org/W3008993296","https://openalex.org/W3009371196","https://openalex.org/W3013658006","https://openalex.org/W3018312910","https://openalex.org/W3021175879","https://openalex.org/W3021669159","https://openalex.org/W3025887701","https://openalex.org/W3036568251","https://openalex.org/W3043010374","https://openalex.org/W3044807520","https://openalex.org/W3072297155","https://openalex.org/W3081427626","https://openalex.org/W3087484287","https://openalex.org/W3087895544","https://openalex.org/W3091174347","https://openalex.org/W3092930902","https://openalex.org/W3093849792","https://openalex.org/W3094183635","https://openalex.org/W3094829982","https://openalex.org/W3098160220","https://openalex.org/W3102980949","https://openalex.org/W3105625590","https://openalex.org/W3112303883","https://openalex.org/W3116394266","https://openalex.org/W3120844131","https://openalex.org/W3121217868","https://openalex.org/W3121726600","https://openalex.org/W3125631070","https://openalex.org/W3129453524","https://openalex.org/W3130747775","https://openalex.org/W3132467470","https://openalex.org/W3156333129","https://openalex.org/W3173284911","https://openalex.org/W3178048855","https://openalex.org/W3180181113","https://openalex.org/W3200627326","https://openalex.org/W3201565887","https://openalex.org/W3204182334","https://openalex.org/W3204620503","https://openalex.org/W3204775905","https://openalex.org/W4221098338","https://openalex.org/W4226418765","https://openalex.org/W4281667098","https://openalex.org/W4283317817","https://openalex.org/W4283329347","https://openalex.org/W4283641397","https://openalex.org/W4285247275","https://openalex.org/W4293528099","https://openalex.org/W4297005784","https://openalex.org/W4308451470","https://openalex.org/W4309154741","https://openalex.org/W4320234102","https://openalex.org/W6641563937","https://openalex.org/W6683932190","https://openalex.org/W6760824235","https://openalex.org/W6764968902","https://openalex.org/W6776625164","https://openalex.org/W6798060926","https://openalex.org/W6802286600","https://openalex.org/W6810269799","https://openalex.org/W6811297763","https://openalex.org/W6849269842"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W4389760904","https://openalex.org/W4306886878","https://openalex.org/W4323520239"],"abstract_inverted_index":{"Machine-learning-based":[0],"text":[1,67,145,168],"classification":[2],"is":[3,78,148],"one":[4],"of":[5,15,39,98,144,167],"the":[6,40,81,84,92,124,130,133,138,165],"leading":[7],"research":[8,35,127,134],"areas":[9],"and":[10,29,46,60,111,115,126],"has":[11],"a":[12],"wide":[13],"range":[14],"applications,":[16],"which":[17],"include":[18],"spam":[19],"detection,":[20],"hate":[21],"speech":[22],"identification,":[23],"reviews,":[24],"rating":[25],"summarization,":[26],"sentiment":[27],"analysis,":[28],"topic":[30],"modelling.":[31],"Widely":[32],"used":[33,79],"machine-learning-based":[34],"differs":[36],"in":[37,91,96,129,137,142,150,164],"terms":[38,97,143],"datasets,":[41,101],"training":[42,110],"methods,":[43,114],"performance":[44,107],"evaluation,":[45],"comparison":[47],"methods":[48],"used.":[49],"In":[50],"this":[51,156],"paper,":[52],"we":[53,122],"surveyed":[54],"224":[55],"papers":[56],"published":[57],"between":[58],"2003":[59],"2022":[61],"that":[62,155],"employed":[63],"machine":[64,102,118],"learning":[65,103,119],"for":[66,73,83,162],"classification.":[68,169],"The":[69,88],"Preferred":[70],"Reporting":[71],"Items":[72],"Systematic":[74],"Reviews":[75],"(PRISMA)":[76],"statement":[77],"as":[80],"guidelines":[82],"systematic":[85],"review":[86],"process.":[87],"comprehensive":[89],"differences":[90],"literature":[93],"are":[94],"analyzed":[95],"six":[99],"aspects:":[100],"models,":[104],"best":[105],"accuracy,":[106],"evaluation":[108],"metrics,":[109],"testing":[112],"splitting":[113],"comparisons":[116],"among":[117],"models.":[120],"Furthermore,":[121],"highlight":[123],"limitations":[125],"gaps":[128],"literature.":[131],"Although":[132],"works":[135],"included":[136],"survey":[139,157],"perform":[140],"well":[141],"classification,":[146],"improvement":[147],"required":[149],"many":[151],"areas.":[152],"We":[153],"believe":[154],"paper":[158],"will":[159],"be":[160],"useful":[161],"researchers":[163],"field":[166]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":7}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}