{"id":"https://openalex.org/W2104294587","doi":"https://doi.org/10.1145/1651343.1651357","title":"Phrase-based document categorization revisited","display_name":"Phrase-based document categorization revisited","publication_year":2009,"publication_date":"2009-11-06","ids":{"openalex":"https://openalex.org/W2104294587","doi":"https://doi.org/10.1145/1651343.1651357","mag":"2104294587"},"language":"en","primary_location":{"id":"doi:10.1145/1651343.1651357","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1651343.1651357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd international workshop on Patent information retrieval","raw_type":"proceedings-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/A5032872149","display_name":"C. H. A. Koster","orcid":"https://orcid.org/0009-0000-3393-6110"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cornelis H.A. Koster","raw_affiliation_strings":["University of Nijmegen, Nijmegen, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nijmegen, Nijmegen, Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004695559","display_name":"Jean Beney","orcid":null},"institutions":[{"id":"https://openalex.org/I48430043","display_name":"Institut National des Sciences Appliqu\u00e9es de Lyon","ror":"https://ror.org/050jn9y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I48430043"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean G. Beney","raw_affiliation_strings":["INSA de Lyon, Lyon, France","INSA de Lyon, Lyon, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INSA de Lyon, Lyon, France","institution_ids":["https://openalex.org/I48430043"]},{"raw_affiliation_string":"INSA de Lyon, Lyon, France#TAB#","institution_ids":["https://openalex.org/I48430043"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3416,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.96421157,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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":0.9998000264167786,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9926999807357788,"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":0.9896000027656555,"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/categorization","display_name":"Categorization","score":0.8650975227355957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7962446212768555},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7396632432937622},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7134060859680176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6326299905776978},{"id":"https://openalex.org/keywords/aka","display_name":"AKA","score":0.6302167773246765},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.6053780913352966},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.561681866645813},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5243285298347473},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.43749701976776123}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8650975227355957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962446212768555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7396632432937622},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7134060859680176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6326299905776978},{"id":"https://openalex.org/C121158502","wikidata":"https://www.wikidata.org/wiki/Q4652161","display_name":"AKA","level":2,"score":0.6302167773246765},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.6053780913352966},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.561681866645813},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5243285298347473},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.43749701976776123},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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":2,"locations":[{"id":"doi:10.1145/1651343.1651357","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1651343.1651357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd international workshop on Patent information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.5909","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.5909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.kun.nl/~kees/home/papers/pair02-koster.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W11171803","https://openalex.org/W578816368","https://openalex.org/W1489959797","https://openalex.org/W1496173351","https://openalex.org/W1530679620","https://openalex.org/W1531820442","https://openalex.org/W1552369012","https://openalex.org/W1552596497","https://openalex.org/W1557758455","https://openalex.org/W1569385487","https://openalex.org/W1576676390","https://openalex.org/W1580052303","https://openalex.org/W1813610639","https://openalex.org/W1973098080","https://openalex.org/W2027512482","https://openalex.org/W2037041009","https://openalex.org/W2045577803","https://openalex.org/W2093756022","https://openalex.org/W2126502509","https://openalex.org/W2129113961","https://openalex.org/W2135114651","https://openalex.org/W2143785854","https://openalex.org/W2149684865","https://openalex.org/W2440833291","https://openalex.org/W4285719527","https://openalex.org/W4289257868","https://openalex.org/W6633067604","https://openalex.org/W6638423001","https://openalex.org/W6680471014","https://openalex.org/W7033031124"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2035261173","https://openalex.org/W2106892947","https://openalex.org/W2237299843"],"abstract_inverted_index":{"This":[0],"paper":[1],"takes":[2],"a":[3],"fresh":[4],"look":[5],"at":[6,83],"an":[7],"old":[8],"idea":[9],"in":[10,21],"Information":[11],"Retrieval:":[12],"the":[13,22,43,51,65,79],"use":[14],"of":[15,27,45],"linguistically":[16],"extracted":[17],"phrases":[18],"as":[19],"terms":[20],"automatic":[23],"categorization":[24,40],"(aka":[25],"classification)":[26],"documents.":[28],"Until":[29],"now,":[30],"there":[31],"was":[32],"found":[33],"little":[34],"or":[35],"no":[36,59],"evidence":[37],"that":[38],"document":[39],"benefits":[41],"from":[42],"application":[44],"linguistics":[46],"techniques.":[47],"Classification":[48],"algorithms":[49],"using":[50,63],"most":[52],"cleverly":[53],"designed":[54],"linguistical":[55,69],"representations":[56],"typically":[57],"do":[58],"better":[60],"than":[61],"those":[62],"simply":[64],"bag-of-words":[66],"representation.":[67],"Shallow":[68],"techniques":[70],"are":[71],"used":[72],"routinely,":[73],"but":[74],"their":[75],"positive":[76],"effect":[77],"on":[78],"accuracy":[80],"is":[81],"small":[82],"best.":[84]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}