{"id":"https://openalex.org/W1539210413","doi":"https://doi.org/10.1007/978-3-642-04417-5_4","title":"Training Data Cleaning for Text Classification","display_name":"Training Data Cleaning for Text Classification","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1539210413","doi":"https://doi.org/10.1007/978-3-642-04417-5_4","mag":"1539210413"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-04417-5_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-04417-5_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5082069715","display_name":"Andrea Esuli","orcid":"https://orcid.org/0000-0002-5725-4322"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Andrea Esuli","raw_affiliation_strings":["Istituto di Scienza e Tecnologia dell\u2019Informazione, Consiglio Nazionale delle Ricerche, Pisa, Italy","Istituto di Scienza e Tecnologia dell'Informazione, Consiglio Nazionale delle Ricerche, Pisa, Italy 56124#TAB#"],"affiliations":[{"raw_affiliation_string":"Istituto di Scienza e Tecnologia dell\u2019Informazione, Consiglio Nazionale delle Ricerche, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]},{"raw_affiliation_string":"Istituto di Scienza e Tecnologia dell'Informazione, Consiglio Nazionale delle Ricerche, Pisa, Italy 56124#TAB#","institution_ids":["https://openalex.org/I122991210"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063975186","display_name":"Fabrizio Sebastiani","orcid":"https://orcid.org/0000-0003-4221-6427"},"institutions":[{"id":"https://openalex.org/I122991210","display_name":"Istituto di Scienza e Tecnologie dell'Informazione \"Alessandro Faedo\"","ror":"https://ror.org/05kacka20","country_code":"IT","type":"facility","lineage":["https://openalex.org/I122991210","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabrizio Sebastiani","raw_affiliation_strings":["Istituto di Scienza e Tecnologia dell\u2019Informazione, Consiglio Nazionale delle Ricerche, Pisa, Italy","Istituto di Scienza e Tecnologia dell'Informazione, Consiglio Nazionale delle Ricerche, Pisa, Italy 56124#TAB#"],"affiliations":[{"raw_affiliation_string":"Istituto di Scienza e Tecnologia dell\u2019Informazione, Consiglio Nazionale delle Ricerche, Pisa, Italy","institution_ids":["https://openalex.org/I122991210"]},{"raw_affiliation_string":"Istituto di Scienza e Tecnologia dell'Informazione, Consiglio Nazionale delle Ricerche, Pisa, Italy 56124#TAB#","institution_ids":["https://openalex.org/I122991210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082069715"],"corresponding_institution_ids":["https://openalex.org/I122991210"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":2.3155,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.89171023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9990000128746033,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9990000128746033,"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/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/T12535","display_name":"Machine Learning and Data Classification","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":0.869706392288208},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.740754246711731},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.7281036376953125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5974408984184265},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5800879001617432},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.5792700052261353},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5782104730606079},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5057699680328369},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4967358708381653},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4724869132041931},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4645642340183258},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4463561475276947},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.42757201194763184},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37678706645965576},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.26059746742248535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.869706392288208},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.740754246711731},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.7281036376953125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5974408984184265},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5800879001617432},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5792700052261353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5782104730606079},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5057699680328369},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4967358708381653},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4724869132041931},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4645642340183258},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4463561475276947},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.42757201194763184},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37678706645965576},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26059746742248535},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-642-04417-5_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-04417-5_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.385.6661","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.385.6661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nmis.isti.cnr.it/sebastiani/Publications/ICTIR09.pdf","raw_type":"text"},{"id":"pmh:oai:dnet:people______::b6c1b1d3cde91d0a06ef26aafdb4a1cf","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S7407055261","display_name":"ISTI Open Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1495524224","https://openalex.org/W1529196404","https://openalex.org/W1588207936","https://openalex.org/W2006873020","https://openalex.org/W2050672162","https://openalex.org/W2053463056","https://openalex.org/W2089421877","https://openalex.org/W2114535528","https://openalex.org/W2135892731","https://openalex.org/W2150102617"],"related_works":["https://openalex.org/W1529840045","https://openalex.org/W4244036394","https://openalex.org/W1842879116","https://openalex.org/W2135107501","https://openalex.org/W2047248895","https://openalex.org/W2124490386","https://openalex.org/W1822895636","https://openalex.org/W2760891738","https://openalex.org/W4317548404","https://openalex.org/W3022007134"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
