{"id":"https://openalex.org/W2293570855","doi":"https://doi.org/10.5220/0005511900260037","title":"A Study on Term Weighting for Text Categorization: A Novel Supervised Variant of tf.idf","display_name":"A Study on Term Weighting for Text Categorization: A Novel Supervised Variant of tf.idf","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2293570855","doi":"https://doi.org/10.5220/0005511900260037","mag":"2293570855"},"language":"en","primary_location":{"id":"doi:10.5220/0005511900260037","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005511900260037","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 4th International Conference on Data Management Technologies and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0005511900260037","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084939540","display_name":"Giacomo Domeniconi","orcid":"https://orcid.org/0000-0003-2797-1547"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Giacomo Domeniconi","raw_affiliation_strings":["University of Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079648393","display_name":"Gianluca Moro","orcid":"https://orcid.org/0000-0002-3663-7877"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gianluca Moro","raw_affiliation_strings":["University of Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069989399","display_name":"Roberto Pasolini","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Pasolini","raw_affiliation_strings":["University of Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":null,"display_name":"Claudio Sartori","orcid":null},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudio Sartori","raw_affiliation_strings":["University of Bologna, Italy"],"affiliations":[{"raw_affiliation_string":"University of Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084939540"],"corresponding_institution_ids":["https://openalex.org/I9360294"],"apc_list":null,"apc_paid":null,"fwci":7.5673,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.97259176,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"37"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9973999857902527,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9918000102043152,"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/weighting","display_name":"Weighting","score":0.9023838043212891},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.7689694166183472},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7662738561630249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7555580735206604},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.7224822640419006},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6973899602890015},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6414034962654114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5485913157463074},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46925756335258484},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.44910383224487305},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41153669357299805},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38924065232276917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.334414541721344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3212314248085022},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14424854516983032}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.9023838043212891},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.7689694166183472},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7662738561630249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555580735206604},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.7224822640419006},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6973899602890015},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6414034962654114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485913157463074},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46925756335258484},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.44910383224487305},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41153669357299805},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38924065232276917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.334414541721344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3212314248085022},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14424854516983032},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0005511900260037","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005511900260037","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 4th International Conference on Data Management Technologies and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/545299","is_oa":false,"landing_page_url":"http://hdl.handle.net/11585/545299","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.5220/0005511900260037","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005511900260037","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 4th International Conference on Data Management Technologies and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W132962688","https://openalex.org/W1493036841","https://openalex.org/W1523389133","https://openalex.org/W1587231733","https://openalex.org/W1595907733","https://openalex.org/W1969128289","https://openalex.org/W1973775139","https://openalex.org/W2024932032","https://openalex.org/W2025954161","https://openalex.org/W2032433809","https://openalex.org/W2075571112","https://openalex.org/W2080214827","https://openalex.org/W2105948726","https://openalex.org/W2109634664","https://openalex.org/W2118020653","https://openalex.org/W2140321362","https://openalex.org/W2149684865","https://openalex.org/W2158903965","https://openalex.org/W2167277498","https://openalex.org/W2911964244"],"related_works":["https://openalex.org/W2017917301","https://openalex.org/W1973723221","https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2372663604","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W1441686524"],"abstract_inverted_index":{"Within":[0],"text":[1,157],"categorization":[2],"and":[3,69,162],"other":[4,70,180],"data":[5],"mining":[6],"tasks,":[7],"the":[8,47,101,107,115,148,169],"use":[9],"of":[10,39,41,87,89,100,114,123,145,184],"suitable":[11],"methods":[12,26,72],"for":[13],"term":[14,24],"weighting":[15,25,71,164],"can":[16],"bring":[17],"a":[18,97],"substantial":[19],"boost":[20],"in":[21,43,54,182],"effectiveness.":[22],"Several":[23],"have":[27],"been":[28],"presented":[29],"throughout":[30],"literature,":[31],"based":[32,84,104,139],"on":[33,85,105,140,154],"assumptions":[34],"commonly":[35],"derived":[36,73],"from":[37,74],"observation":[38],"distribution":[40],"words":[42,52,146],"documents.":[44],"For":[45],"example,":[46],"idf":[48,109],"assumption":[49],"states":[50],"that":[51,121,168],"appearing":[53,126],"many":[55],"documents":[56,91,113],"are":[57,81],"usually":[58],"not":[59,131],"as":[60,62],"important":[61],"less":[63],"frequent":[64],"ones.":[65],"Contrarily":[66],"to":[67,92,117,179],"tf.idf":[68,102],"information":[75],"retrieval,":[76],"schemes":[77],"proposed":[78,135],"more":[79],"recently":[80],"supervised,":[82],"i.e.":[83],"knownledge":[86],"membership":[88],"training":[90],"categories.":[93],"We":[94],"propose":[95,172],"here":[96],"supervised":[98,163],"variant":[99,136],"scheme,":[103],"computing":[106],"usual":[108],"factor":[110],"without":[111],"considering":[112,143],"category":[116,149],"be":[118],"recognized,":[119],"so":[120],"importance":[122],"terms":[124,183],"frequently":[125],"only":[127],"within":[128,147],"it":[129],"is":[130,137],"underestimated.":[132],"A":[133],"further":[134],"additionally":[138],"relevance":[141],"frequency,":[142],"occurrences":[144],"itself.":[150],"In":[151],"extensive":[152],"experiments":[153],"two":[155,187],"recurring":[156],"collections":[158],"with":[159],"several":[160],"unsupervised":[161],"schemes,":[165],"we":[166,171],"show":[167],"ones":[170,181],"generally":[173],"perform":[174],"better":[175],"than":[176],"or":[177],"comparably":[178],"accuracy,":[185],"using":[186],"different":[188],"learning":[189],"methods.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}