{"id":"https://openalex.org/W1524564918","doi":"https://doi.org/10.1007/978-3-642-01818-3_35","title":"An Empirical Study of Category Skew on Feature Selection for Text Categorization","display_name":"An Empirical Study of Category Skew on Feature Selection for Text Categorization","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1524564918","doi":"https://doi.org/10.1007/978-3-642-01818-3_35","mag":"1524564918"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-01818-3_35","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-01818-3_35","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":"conference-paper","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/A5080107674","display_name":"Mondelle Simeon","orcid":null},"institutions":[{"id":"https://openalex.org/I194028371","display_name":"University of Regina","ror":"https://ror.org/03dzc0485","country_code":"CA","type":"education","lineage":["https://openalex.org/I194028371"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mondelle Simeon","raw_affiliation_strings":["Department of Computer Science, University of Regina, Regina, Saskatchewan, S4S 0A2, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Regina, Regina, Saskatchewan, S4S 0A2, Canada","institution_ids":["https://openalex.org/I194028371"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069034771","display_name":"Robert J. Hilderman","orcid":null},"institutions":[{"id":"https://openalex.org/I194028371","display_name":"University of Regina","ror":"https://ror.org/03dzc0485","country_code":"CA","type":"education","lineage":["https://openalex.org/I194028371"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Robert Hilderman","raw_affiliation_strings":["Department of Computer Science, University of Regina, Regina, Saskatchewan, S4S 0A2, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Regina, Regina, Saskatchewan, S4S 0A2, Canada","institution_ids":["https://openalex.org/I194028371"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I194028371"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03576117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"249","last_page":"252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9951000213623047,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9905999898910522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.8327051401138306},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.8282754421234131},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7725827693939209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7019826769828796},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6675399541854858},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.6181345582008362},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6056780815124512},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.571925163269043},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5456008911132812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5360057353973389},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3908776640892029},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3496977686882019},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31328168511390686}],"concepts":[{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.8327051401138306},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.8282754421234131},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7725827693939209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7019826769828796},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6675399541854858},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.6181345582008362},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6056780815124512},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.571925163269043},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5456008911132812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5360057353973389},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3908776640892029},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3496977686882019},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31328168511390686},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-01818-3_35","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-01818-3_35","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:10.1.1.161.1604","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.1604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2.cs.uregina.ca/~hilder/refereed_conference_proceedings/canai09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1378570","https://openalex.org/W99763903","https://openalex.org/W140777655","https://openalex.org/W1714192071","https://openalex.org/W1879009681","https://openalex.org/W2118020653","https://openalex.org/W2135813353","https://openalex.org/W2149684865","https://openalex.org/W2435251607","https://openalex.org/W2505312721","https://openalex.org/W2959877194","https://openalex.org/W3120740533","https://openalex.org/W6600135713"],"related_works":["https://openalex.org/W2952178725","https://openalex.org/W4299320219","https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2078570174","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}