{"id":"https://openalex.org/W2000918452","doi":"https://doi.org/10.1145/1281192.1281260","title":"A concept-based model for enhancing text categorization","display_name":"A concept-based model for enhancing text categorization","publication_year":2007,"publication_date":"2007-08-12","ids":{"openalex":"https://openalex.org/W2000918452","doi":"https://doi.org/10.1145/1281192.1281260","mag":"2000918452"},"language":"en","primary_location":{"id":"doi:10.1145/1281192.1281260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281192.1281260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"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/A5075022926","display_name":"Shady Shehata","orcid":"https://orcid.org/0000-0002-3258-6734"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shady Shehata","raw_affiliation_strings":["University of Waterloo","(University of Waterloo)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"(University of Waterloo)","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070046659","display_name":"Fakhri Karray","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fakhri Karray","raw_affiliation_strings":["University of Waterloo","(University of Waterloo)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"(University of Waterloo)","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318050","display_name":"Mohamed S. Kamel","orcid":"https://orcid.org/0000-0001-6173-8082"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohamed Kamel","raw_affiliation_strings":["University of Waterloo","(University of Waterloo)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"(University of Waterloo)","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"629","last_page":"637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7496225833892822},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7094098925590515},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6790323853492737},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6569390296936035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5892667770385742},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5681118965148926},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5610414743423462},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5221845507621765},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4720498025417328},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32736754417419434},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.16564911603927612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7496225833892822},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7094098925590515},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6790323853492737},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6569390296936035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5892667770385742},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5681118965148926},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5610414743423462},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5221845507621765},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4720498025417328},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32736754417419434},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.16564911603927612},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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":1,"locations":[{"id":"doi:10.1145/1281192.1281260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281192.1281260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W182831726","https://openalex.org/W1956559956","https://openalex.org/W2092654472","https://openalex.org/W2098162425","https://openalex.org/W2107131706","https://openalex.org/W2107134232","https://openalex.org/W2112378479","https://openalex.org/W2134199742","https://openalex.org/W2138043057","https://openalex.org/W2149684865","https://openalex.org/W2150203234","https://openalex.org/W2151170651","https://openalex.org/W2165612380","https://openalex.org/W2797128378","https://openalex.org/W2885050925","https://openalex.org/W2911854988","https://openalex.org/W4401102731"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2180954594","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2052835778","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540"],"abstract_inverted_index":{"Most":[0],"of":[1,12,17,24,49,67,81,89,110,144,202,233,245,276],"text":[2,212],"categorization":[3,213],"techniques":[4],"are":[5,181,194,263],"based":[6],"on":[7,99,208,249],"word":[8],"and/or":[9],"phrase":[10],"analysis":[11,16,109],"the":[13,22,25,36,47,53,57,72,79,82,87,90,100,107,133,137,159,168,173,197,205,219,225,230,234,239,253,257,266,274],"text.":[14,68],"Statistical":[15],"a":[18,28,184],"term":[19,26,44,155],"frequency":[20,38],"captures":[21],"importance":[23],"within":[27],"document":[29,103,111],"only.":[30],"However,":[31],"two":[32,164,179,250],"terms":[33,62,76,98,123,130],"can":[34,74,118],"have":[35,190],"same":[37],"in":[39,211],"their":[40],"documents,":[41],"but":[42],"one":[43],"contributes":[45,157],"moreto":[46],"meaning":[48],"its":[50],"sentences":[51],"than":[52,106],"other":[54],"term.":[55],"Thus,":[56],"underlying":[58],"model":[59,73,95,117,142,269],"should":[60],"indicate":[61],"that":[63,77,96,135,189],"capture":[64,75],"these":[65],"mantics":[66],"In":[69],"this":[70],"case,":[71],"present":[78],"concepts":[80,134,188],"sentence,":[83],"which":[84,131,156],"leads":[85],"todiscover":[86],"topic":[88],"document.":[91],"A":[92,200],"new":[93,185],"concept-based":[94,116,145,169,226,235],"analyzes":[97],"sentence":[101,127,138,160],"and":[102,129,172,224,238,256],"levels":[104],"rather":[105],"traditional":[108,222],"only":[112],"is":[113,162,214,247,270],"introduced.":[114],"The":[115,140,154,187,216,243],"effectively":[119],"discriminate":[120],"between":[121,221],"non-important":[122],"with":[124],"respect":[125],"to":[126,158,272],"semantics":[128,161],"hold":[132],"represent":[136],"meaning.":[139],"proposed":[141,206],"consists":[143],"statistical":[146,170,236],"analyzer,":[147],"conceptual":[148,174,240],"ontological":[149,175,241],"graph":[150,176],"representation,and":[151],"concept":[152,198],"extractor.":[153,199],"assigned":[163],"different":[165,209],"weights":[166,180,193],"by":[167,196,229],"analyzer":[171,237],"representation.":[177],"These":[178,260],"combined":[182,192,231],"into":[183],"weight.":[186],"maximum":[191],"selected":[195],"set":[201],"experiments":[203,217],"using":[204],"concept-basedmodel":[207],"datasets":[210],"conducted.":[215],"demonstrate":[218],"comparison":[220],"weighting":[223,227],"obtained":[228],"approach":[232],"graph.":[242],"evaluation":[244],"results":[246],"relied":[248],"quality":[251,261,275],"measures,":[252],"Macro-averaged":[254],"F1":[255],"Error":[258],"rate.":[259],"measures":[262],"improved":[264],"when":[265],"newly":[267],"developedconcept-based":[268],"used":[271],"enhance":[273],"thetext":[277],"categorization.":[278]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}