{"id":"https://openalex.org/W2044800400","doi":"https://doi.org/10.1007/s10791-008-9083-7","title":"Using the Web as corpus for self-training text categorization","display_name":"Using the Web as corpus for self-training text categorization","publication_year":2008,"publication_date":"2008-12-22","ids":{"openalex":"https://openalex.org/W2044800400","doi":"https://doi.org/10.1007/s10791-008-9083-7","mag":"2044800400"},"language":"en","primary_location":{"id":"doi:10.1007/s10791-008-9083-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10791-008-9083-7","pdf_url":null,"source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval","raw_type":"journal-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/A5030185432","display_name":"Rafael Guzm\u00e1n-Cabrera","orcid":"https://orcid.org/0000-0002-9320-7021"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]},{"id":"https://openalex.org/I129858807","display_name":"Universidad de Guanajuato","ror":"https://ror.org/058cjye32","country_code":"MX","type":"education","lineage":["https://openalex.org/I129858807"]}],"countries":["ES","MX"],"is_corresponding":true,"raw_author_name":"Rafael Guzm\u00e1n-Cabrera","raw_affiliation_strings":["Facultad de Ingenier\u00eda Mec\u00e1nica, Electrica y Electr\u00f3nica, Universidad de Guanajuato, Guanajuato, Mexico","Natural Language Engineering Lab., Polytechnic University of Valencia, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Facultad de Ingenier\u00eda Mec\u00e1nica, Electrica y Electr\u00f3nica, Universidad de Guanajuato, Guanajuato, Mexico","institution_ids":["https://openalex.org/I129858807"]},{"raw_affiliation_string":"Natural Language Engineering Lab., Polytechnic University of Valencia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050780136","display_name":"Manuel Montes-y-G\u00f3mez","orcid":"https://orcid.org/0000-0002-7601-501X"},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Manuel Montes-y-G\u00f3mez","raw_affiliation_strings":["Laboratorio de Tecnolog\u00edas del Lenguaje, Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica, Tonantzintla, Mexico"],"affiliations":[{"raw_affiliation_string":"Laboratorio de Tecnolog\u00edas del Lenguaje, Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica, Tonantzintla, Mexico","institution_ids":["https://openalex.org/I39824353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053947754","display_name":"Paolo Rosso","orcid":"https://orcid.org/0000-0002-8922-1242"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Paolo Rosso","raw_affiliation_strings":["Natural Language Engineering Lab., Polytechnic University of Valencia, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Natural Language Engineering Lab., Polytechnic University of Valencia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053929522","display_name":"Luis Villase\u00f1or-Pineda","orcid":"https://orcid.org/0000-0003-1294-9128"},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Luis Villase\u00f1or-Pineda","raw_affiliation_strings":["Laboratorio de Tecnolog\u00edas del Lenguaje, Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica, Tonantzintla, Mexico"],"affiliations":[{"raw_affiliation_string":"Laboratorio de Tecnolog\u00edas del Lenguaje, Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica, Tonantzintla, Mexico","institution_ids":["https://openalex.org/I39824353"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030185432"],"corresponding_institution_ids":["https://openalex.org/I129858807","https://openalex.org/I60053951"],"apc_list":null,"apc_paid":null,"fwci":4.1276,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.93667302,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"12","issue":"3","first_page":"400","last_page":"415"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9941999912261963,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9909999966621399,"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":0.8099762201309204},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7415508031845093},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.716583251953125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6466031670570374},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5890657305717468},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.566543459892273},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5565259456634521},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4729708731174469},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4566743075847626},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.42919057607650757},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4116330146789551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8099762201309204},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7415508031845093},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.716583251953125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6466031670570374},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5890657305717468},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.566543459892273},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5565259456634521},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4729708731174469},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4566743075847626},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.42919057607650757},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4116330146789551},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10791-008-9083-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10791-008-9083-7","pdf_url":null,"source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Retrieval","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W176996","https://openalex.org/W84750871","https://openalex.org/W137381505","https://openalex.org/W1521373230","https://openalex.org/W1570448133","https://openalex.org/W1574877594","https://openalex.org/W1602390003","https://openalex.org/W1606247040","https://openalex.org/W1841211639","https://openalex.org/W1941537533","https://openalex.org/W1990190154","https://openalex.org/W2014516359","https://openalex.org/W2031253971","https://openalex.org/W2053724458","https://openalex.org/W2097089247","https://openalex.org/W2097532520","https://openalex.org/W2107008379","https://openalex.org/W2118020653","https://openalex.org/W2123504579","https://openalex.org/W2136504847","https://openalex.org/W2151752770","https://openalex.org/W2165281381","https://openalex.org/W2179799930","https://openalex.org/W2797694932","https://openalex.org/W2912780347","https://openalex.org/W3100051113","https://openalex.org/W4243957593","https://openalex.org/W6680140577","https://openalex.org/W6992441829","https://openalex.org/W7055702063","https://openalex.org/W7058186782"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2035261173","https://openalex.org/W2138922887","https://openalex.org/W2383063829","https://openalex.org/W2082678934","https://openalex.org/W2106892947","https://openalex.org/W2168489430"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
