{"id":"https://openalex.org/W3146886606","doi":"https://doi.org/10.1007/s42979-021-00480-4","title":"Simple Baseline Machine Learning Text Classifiers for Small Datasets","display_name":"Simple Baseline Machine Learning Text Classifiers for Small Datasets","publication_year":2021,"publication_date":"2021-03-30","ids":{"openalex":"https://openalex.org/W3146886606","doi":"https://doi.org/10.1007/s42979-021-00480-4","mag":"3146886606"},"language":"en","primary_location":{"id":"doi:10.1007/s42979-021-00480-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-021-00480-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42979-021-00480-4.pdf","source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s42979-021-00480-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019850639","display_name":"Martin Riekert","orcid":"https://orcid.org/0000-0003-4859-6627"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Riekert","raw_affiliation_strings":["Eberhard Karls University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4859-6627","affiliations":[{"raw_affiliation_string":"Eberhard Karls University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075896368","display_name":"Matthias Riekert","orcid":"https://orcid.org/0000-0003-4522-9207"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Martin Riekert","raw_affiliation_strings":["Eberhard Karls University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4859-6627","affiliations":[{"raw_affiliation_string":"Eberhard Karls University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075896368","display_name":"Matthias Riekert","orcid":"https://orcid.org/0000-0003-4522-9207"},"institutions":[{"id":"https://openalex.org/I110079840","display_name":"University of Hohenheim","ror":"https://ror.org/00b1c9541","country_code":"DE","type":"education","lineage":["https://openalex.org/I110079840"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Matthias Riekert","raw_affiliation_strings":["Eberhard Karls University of T\u00fcbingen, T\u00fcbingen, Germany","University of Hohenheim, Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4522-9207","affiliations":[{"raw_affiliation_string":"Eberhard Karls University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"University of Hohenheim, Stuttgart, Germany","institution_ids":["https://openalex.org/I110079840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075896368","display_name":"Matthias Riekert","orcid":"https://orcid.org/0000-0003-4522-9207"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Riekert","raw_affiliation_strings":["Eberhard Karls University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4522-9207","affiliations":[{"raw_affiliation_string":"Eberhard Karls University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067995345","display_name":"Achim Klein","orcid":null},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Achim Klein","raw_affiliation_strings":["Eberhard Karls University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eberhard Karls University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075896368"],"corresponding_institution_ids":["https://openalex.org/I110079840","https://openalex.org/I8087733"],"apc_list":{"value":3190,"currency":"USD","value_usd":3190},"apc_paid":{"value":3190,"currency":"USD","value_usd":3190},"fwci":1.346,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83642121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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/T11644","display_name":"Spam and Phishing Detection","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.996999979019165,"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":0.7555492520332336},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6407227516174316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6271175146102905},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6141867637634277},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6082029938697815},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.558991014957428},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5152945518493652},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5037676692008972},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47128811478614807},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4604448080062866},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3416271209716797},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12937170267105103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555492520332336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6407227516174316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6271175146102905},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6141867637634277},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6082029938697815},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.558991014957428},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5152945518493652},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5037676692008972},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47128811478614807},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4604448080062866},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3416271209716797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12937170267105103},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s42979-021-00480-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-021-00480-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42979-021-00480-4.pdf","source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s42979-021-00480-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-021-00480-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42979-021-00480-4.pdf","source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G735684994","display_name":null,"funder_award_id":"03EGSBW498","funder_id":"https://openalex.org/F4320323803","funder_display_name":"Bundesministerium f\u00fcr Wirtschaft und Energie"}],"funders":[{"id":"https://openalex.org/F4320323803","display_name":"Bundesministerium f\u00fcr Wirtschaft und Energie","ror":"https://ror.org/02vgg2808"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3146886606.pdf","grobid_xml":"https://content.openalex.org/works/W3146886606.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1532325895","https://openalex.org/W1540550673","https://openalex.org/W1680392829","https://openalex.org/W1978394996","https://openalex.org/W2024932032","https://openalex.org/W2035265584","https://openalex.org/W2049129660","https://openalex.org/W2063596712","https://openalex.org/W2079656678","https://openalex.org/W2079823081","https://openalex.org/W2087347434","https://openalex.org/W2092971502","https://openalex.org/W2101234009","https://openalex.org/W2109634664","https://openalex.org/W2113459411","https://openalex.org/W2118020653","https://openalex.org/W2118027802","https://openalex.org/W2118585731","https://openalex.org/W2120400822","https://openalex.org/W2132886902","https://openalex.org/W2134429390","https://openalex.org/W2149684865","https://openalex.org/W2154359981","https://openalex.org/W2154776925","https://openalex.org/W2166706824","https://openalex.org/W2170240176","https://openalex.org/W2287044641","https://openalex.org/W2517227754","https://openalex.org/W2570737513","https://openalex.org/W2593681087","https://openalex.org/W2625464253","https://openalex.org/W2787894218","https://openalex.org/W2800318991","https://openalex.org/W2808126995","https://openalex.org/W2898339904","https://openalex.org/W2919115771","https://openalex.org/W2960456850","https://openalex.org/W2963026768","https://openalex.org/W2963341956","https://openalex.org/W2963433607","https://openalex.org/W2965552599","https://openalex.org/W2981842822","https://openalex.org/W2993506183","https://openalex.org/W2995683177","https://openalex.org/W3021829213","https://openalex.org/W3088577908","https://openalex.org/W3105951585","https://openalex.org/W3122944446","https://openalex.org/W3123492911","https://openalex.org/W4213009331","https://openalex.org/W4240908132","https://openalex.org/W4285719527","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W2280638972","https://openalex.org/W3145898297","https://openalex.org/W2357114597","https://openalex.org/W2115416187","https://openalex.org/W114581555"],"abstract_inverted_index":{"Abstract":[0],"Text":[1],"classification":[2,160],"is":[3,21,122],"important":[4],"to":[5,26,46,58],"better":[6],"understand":[7],"online":[8,131],"media.":[9],"A":[10],"major":[11,120],"problem":[12],"for":[13,114,129],"creating":[14,130],"accurate":[15],"text":[16,41,94,133,146],"classifiers":[17,42,134],"using":[18,135,165],"machine":[19],"learning":[20],"small":[22,136],"training":[23,53,81,87,108,137],"sets":[24,54,88],"due":[25],"the":[27,52,98],"cost":[28],"of":[29,70,91,101,125,170],"annotating":[30],"them.":[31],"On":[32],"this":[33],"basis,":[34],"we":[35],"investigated":[36],"how":[37,51],"SVM":[38],"and":[39,50,142,151],"NBSVM":[40],"should":[43,55],"be":[44,56,163],"designed":[45],"achieve":[47],"high":[48,159],"accuracy":[49,102,112,161],"sized":[57],"efficiently":[59],"use":[60],"annotation":[61],"labor.":[62],"We":[63,96,139],"used":[64],"a":[65,123,152,166],"four-way":[66],"repeated-measures":[67],"full-factorial":[68],"design":[69,72,77],"32":[71],"factor":[73,78],"combinations.":[74],"For":[75],"each":[76],"combination":[79],"22":[80],"set":[82,124],"sizes":[83],"were":[84,89],"examined.":[85],"These":[86],"subsets":[90],"seven":[92],"public":[93],"datasets.":[95],"study":[97],"statistical":[99],"variance":[100],"estimates":[103,113],"by":[104],"randomly":[105],"drawing":[106],"new":[107],"sets,":[109],"resulting":[110],"in":[111],"98,560":[115],"different":[116],"experimental":[117],"runs.":[118],"Our":[119,155],"contribution":[121],"empirically":[126],"evaluated":[127],"guidelines":[128],"media":[132],"sets.":[138],"recommend":[140],"uni-":[141],"bi-gram":[143],"features":[144],"as":[145],"representation,":[147],"btc":[148],"term":[149],"weighting":[150],"linear-kernel":[153],"NBSVM.":[154],"results":[156],"suggest":[157],"that":[158],"can":[162],"achieved":[164],"manually":[167],"annotated":[168],"dataset":[169],"only":[171],"300":[172],"examples.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}