{"id":"https://openalex.org/W2022780779","doi":"https://doi.org/10.5539/cis.v4n6p48","title":"Semi-Automatic Labeling of Training Data Sets in Text Classification","display_name":"Semi-Automatic Labeling of Training Data Sets in Text Classification","publication_year":2011,"publication_date":"2011-10-27","ids":{"openalex":"https://openalex.org/W2022780779","doi":"https://doi.org/10.5539/cis.v4n6p48","mag":"2022780779"},"language":"en","primary_location":{"id":"doi:10.5539/cis.v4n6p48","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v4n6p48","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/10419/8914","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ccsenet.org/journal/index.php/cis/article/download/10419/8914","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051407448","display_name":"Nayereh Ghahreman","orcid":null},"institutions":[{"id":"https://openalex.org/I39268498","display_name":"University of Isfahan","ror":"https://ror.org/05h9t7759","country_code":"IR","type":"education","lineage":["https://openalex.org/I39268498"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Nayereh Ghahreman","raw_affiliation_strings":["Department of Computer Engineering, University of Isfahan, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, University of Isfahan, Iran","institution_ids":["https://openalex.org/I39268498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110388734","display_name":"Ahmad Baraani Dastjerdi","orcid":null},"institutions":[{"id":"https://openalex.org/I39268498","display_name":"University of Isfahan","ror":"https://ror.org/05h9t7759","country_code":"IR","type":"education","lineage":["https://openalex.org/I39268498"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ahmad Baraani Dastjerdi","raw_affiliation_strings":["Department of Computer Engineering, University of Isfahan, Iran","University  of Isfahan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, University of Isfahan, Iran","institution_ids":["https://openalex.org/I39268498"]},{"raw_affiliation_string":"University  of Isfahan","institution_ids":["https://openalex.org/I39268498"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I39268498"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.09721493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":94},"biblio":{"volume":"4","issue":"6","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":0.9995999932289124,"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":0.9995999932289124,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9883000254631042,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9879000186920166,"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/carelessness","display_name":"Carelessness","score":0.9386194944381714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8839058876037598},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.67335045337677},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6218199133872986},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6053090691566467},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5856423377990723},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5339692234992981},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4777635633945465},{"id":"https://openalex.org/keywords/data-reduction","display_name":"Data reduction","score":0.47008442878723145},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45986199378967285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.421627402305603},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.41836434602737427}],"concepts":[{"id":"https://openalex.org/C2779837783","wikidata":"https://www.wikidata.org/wiki/Q691101","display_name":"Carelessness","level":2,"score":0.9386194944381714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8839058876037598},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.67335045337677},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6218199133872986},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6053090691566467},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5856423377990723},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5339692234992981},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4777635633945465},{"id":"https://openalex.org/C153914771","wikidata":"https://www.wikidata.org/wiki/Q5227343","display_name":"Data reduction","level":2,"score":0.47008442878723145},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45986199378967285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.421627402305603},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.41836434602737427},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5539/cis.v4n6p48","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v4n6p48","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/10419/8914","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.660.4545","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.660.4545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ccsenet.org/journal/index.php/cis/article/download/10419/8914/","raw_type":"text"}],"best_oa_location":{"id":"doi:10.5539/cis.v4n6p48","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v4n6p48","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/10419/8914","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2022780779.pdf","grobid_xml":"https://content.openalex.org/works/W2022780779.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W740415","https://openalex.org/W1577933906","https://openalex.org/W1982589161","https://openalex.org/W1985303292","https://openalex.org/W1999635750","https://openalex.org/W2008407812","https://openalex.org/W2017167913","https://openalex.org/W2043976122","https://openalex.org/W2085256060","https://openalex.org/W2091669653","https://openalex.org/W2118020653","https://openalex.org/W2135813353","https://openalex.org/W2138745909","https://openalex.org/W2139212933","https://openalex.org/W2149684865","https://openalex.org/W2156909104","https://openalex.org/W2170654002","https://openalex.org/W4232598318","https://openalex.org/W6683581212"],"related_works":["https://openalex.org/W2022780779","https://openalex.org/W2161052216","https://openalex.org/W4317548404","https://openalex.org/W3022007134","https://openalex.org/W2949671220","https://openalex.org/W2130553454","https://openalex.org/W3132346564","https://openalex.org/W2991483587","https://openalex.org/W2786391746","https://openalex.org/W1975718549"],"abstract_inverted_index":{"Web":[0],"includes":[1],"digital":[2],"libraries":[3],"and":[4,11,22,49,75,87,122,186],"billions":[5],"of":[6,70,93,99,114,137,150],"text":[7,44],"documents.":[8],"A":[9],"fast":[10],"simple":[12],"search":[13],"through":[14],"this":[15,95,115,157,173],"sizeable":[16],"set":[17,102],"is":[18,31,72,90,119,126,153,175],"important":[19],"for":[20,168],"users":[21],"researchers.":[23],"Since":[24],"manual":[25,81],"or":[26],"rule":[27],"based":[28],"document":[29],"classification":[30,38,45],"a":[32,73,107,111],"difficult,":[33],"time":[34,76],"consuming":[35,77],"process,":[36],"automatic":[37],"systems":[39,46],"are":[40,63],"absolutely":[41],"needed.":[42],"Automatic":[43],"demand":[47],"extensive":[48,116],"proper":[50],"training":[51,100,139],"data":[52,57,101,165,171],"sets.":[53],"To":[54],"provide":[55],"these":[56],"sets,":[58,166,172],"usually,":[59],"numerous":[60],"unlabeled":[61],"documents":[62,71,118,142],"labeled":[64,120,146],"manually":[65,121],"by":[66,132,183],"experts.":[67],"Manual":[68],"labeling":[69,133],"difficult":[74],"process.":[78],"Moreover,":[79],"in":[80,106,159,163],"labeling,":[82],"due":[83],"to":[84,178],"human":[85,184],"exhaustion":[86,185],"carelessness,":[88],"there":[89],"the":[91,123,138,179],"possibility":[92],"mistakes.In":[94],"study,":[96],"semi-automatic":[97],"creation":[98],"has":[103],"been":[104],"proposed":[105],"way":[108],"that":[109,131,156],"only":[110,134,161],"small":[112],"percentage":[113,125],"set\u2019s":[117],"remaining":[124,141],"done":[127],"automatically.":[128],"Results":[129],"show":[130],"ten":[135],"percent":[136,149],"set,":[140],"can":[143],"be":[144],"automatically":[145],"with":[147],"98":[148],"accuracy.":[151],"It":[152],"worth":[154],"mentioning":[155],"reduction":[158,174,181],"accuracy":[160,180],"occurs":[162],"standard":[164],"while":[167],"large":[169],"practical":[170],"trivial":[176],"compared":[177],"resulted":[182],"carelessness.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
