{"id":"https://openalex.org/W2113620787","doi":"https://doi.org/10.1177/0165551514550143","title":"A novel feature selection method for text classification using association rules and clustering","display_name":"A novel feature selection method for text classification using association rules and clustering","publication_year":2014,"publication_date":"2014-10-03","ids":{"openalex":"https://openalex.org/W2113620787","doi":"https://doi.org/10.1177/0165551514550143","mag":"2113620787"},"language":"en","primary_location":{"id":"doi:10.1177/0165551514550143","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551514550143","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.tees.ac.uk/en/publications/4856402e-b9ff-4f17-92ff-fc4c2036a1ff","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070370221","display_name":"Navid Sheydaei","orcid":null},"institutions":[{"id":"https://openalex.org/I170013655","display_name":"Isfahan University of Technology","ror":"https://ror.org/00af3sa43","country_code":"IR","type":"education","lineage":["https://openalex.org/I170013655"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Navid Sheydaei","raw_affiliation_strings":["Department of Computer Engineering, Isfahan University of Technology, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Isfahan University of Technology, Iran","institution_ids":["https://openalex.org/I170013655"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051059716","display_name":"Mohamad Saraee","orcid":"https://orcid.org/0000-0002-3283-1912"},"institutions":[{"id":"https://openalex.org/I54459138","display_name":"University of Salford","ror":"https://ror.org/01tmqtf75","country_code":"GB","type":"education","lineage":["https://openalex.org/I54459138"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mohamad Saraee","raw_affiliation_strings":["School of Computing, Science and Engineering, University of Salford-Manchester, UK","School of Computing, Science and Engineering, University of Salford Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Science and Engineering, University of Salford-Manchester, UK","institution_ids":["https://openalex.org/I54459138"]},{"raw_affiliation_string":"School of Computing, Science and Engineering, University of Salford Manchester, UK","institution_ids":["https://openalex.org/I54459138"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040704479","display_name":"Azar Shahgholian","orcid":"https://orcid.org/0000-0002-8551-2296"},"institutions":[{"id":"https://openalex.org/I170013655","display_name":"Isfahan University of Technology","ror":"https://ror.org/00af3sa43","country_code":"IR","type":"education","lineage":["https://openalex.org/I170013655"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Azar Shahgholian","raw_affiliation_strings":["Department of Computer Engineering, Isfahan University of Technology, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Isfahan University of Technology, Iran","institution_ids":["https://openalex.org/I170013655"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8993,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92224612,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"41","issue":"1","first_page":"3","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9937000274658203,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9927999973297119,"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":0.7608929872512817},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7405182719230652},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7100201845169067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6774102449417114},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5850754380226135},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.5536681413650513},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.55222088098526},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5317180156707764},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.521798849105835},{"id":"https://openalex.org/keywords/association-rule-learning","display_name":"Association rule learning","score":0.5202687978744507},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5005953311920166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4920324981212616},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.48663529753685},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.44765201210975647},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.436939001083374},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.429452508687973},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09473264217376709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608929872512817},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7405182719230652},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7100201845169067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6774102449417114},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5850754380226135},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.5536681413650513},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.55222088098526},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5317180156707764},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.521798849105835},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.5202687978744507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5005953311920166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4920324981212616},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.48663529753685},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.44765201210975647},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.436939001083374},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.429452508687973},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09473264217376709},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1177/0165551514550143","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551514550143","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"},{"id":"pmh:oai:https://research.tees.ac.uk/ws/oai:openaire/4856402e-b9ff-4f17-92ff-fc4c2036a1ff","is_oa":true,"landing_page_url":"https://research.tees.ac.uk/en/publications/4856402e-b9ff-4f17-92ff-fc4c2036a1ff","pdf_url":null,"source":{"id":"https://openalex.org/S4306401198","display_name":"TeesRep (Teesside University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I874055015","host_organization_name":"Teesside University","host_organization_lineage":["https://openalex.org/I874055015"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sheydaei, N, Saraee, M & Shahgholian, A 2015, 'A novel feature selection method for text classification using association rules and clustering', Journal of Information Science, pp. -. https://doi.org/10.1177/0165551514550143","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/e4d08e40-6f0d-4dae-bc5a-65b93b3bfada","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/e4d08e40-6f0d-4dae-bc5a-65b93b3bfada","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sheydaei, N, Saraee, M & Shahgholian, A 2015, 'A novel feature selection method for text classification using association rules and clustering', Journal of Information Science, vol. 41, no. 1, pp. 3-15. https://doi.org/10.1177/0165551514550143","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:researchonline.ljmu.ac.uk:9448","is_oa":false,"landing_page_url":"https://researchonline.ljmu.ac.uk/id/eprint/9448/8/JIS-2545-accepted.docx","pdf_url":null,"source":{"id":"https://openalex.org/S4306401246","display_name":"Liverpool John Moores University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63098007","host_organization_name":"Liverpool John Moores University","host_organization_lineage":["https://openalex.org/I63098007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:tees.openrepository.com:10149/621049","is_oa":false,"landing_page_url":"http://hdl.handle.net/10149/621049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:usir.salford.ac.uk:33617","is_oa":true,"landing_page_url":"http://usir.salford.ac.uk/id/eprint/33617/1/USIR_33617_A%20novel%20feature%20selection%20method.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401501","display_name":"University of Salford Institutional Repository (University of Salford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I54459138","host_organization_name":"University of Salford","host_organization_lineage":["https://openalex.org/I54459138"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:https://research.tees.ac.uk/ws/oai:openaire/4856402e-b9ff-4f17-92ff-fc4c2036a1ff","is_oa":true,"landing_page_url":"https://research.tees.ac.uk/en/publications/4856402e-b9ff-4f17-92ff-fc4c2036a1ff","pdf_url":null,"source":{"id":"https://openalex.org/S4306401198","display_name":"TeesRep (Teesside University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I874055015","host_organization_name":"Teesside University","host_organization_lineage":["https://openalex.org/I874055015"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sheydaei, N, Saraee, M & Shahgholian, A 2015, 'A novel feature selection method for text classification using association rules and clustering', Journal of Information Science, pp. -. https://doi.org/10.1177/0165551514550143","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311740","display_name":"University of Salford Manchester","ror":"https://ror.org/01tmqtf75"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W140890161","https://openalex.org/W172811727","https://openalex.org/W203142680","https://openalex.org/W1484413656","https://openalex.org/W1496655772","https://openalex.org/W1506285740","https://openalex.org/W1531743498","https://openalex.org/W1623342295","https://openalex.org/W1907020532","https://openalex.org/W1965667542","https://openalex.org/W2018605192","https://openalex.org/W2037074646","https://openalex.org/W2063862666","https://openalex.org/W2064853889","https://openalex.org/W2084812512","https://openalex.org/W2097726431","https://openalex.org/W2108923196","https://openalex.org/W2115482638","https://openalex.org/W2117423052","https://openalex.org/W2120011452","https://openalex.org/W2132520255","https://openalex.org/W2142827986","https://openalex.org/W2154642793","https://openalex.org/W2160660844","https://openalex.org/W2166559705","https://openalex.org/W2167681385","https://openalex.org/W2168133915","https://openalex.org/W2607336911","https://openalex.org/W2756666283","https://openalex.org/W2913593077","https://openalex.org/W2982720039","https://openalex.org/W4205184193","https://openalex.org/W4252403066","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2534020605","https://openalex.org/W2391234281","https://openalex.org/W2038759274","https://openalex.org/W3200179079","https://openalex.org/W1528447234","https://openalex.org/W2410489130","https://openalex.org/W1598005466","https://openalex.org/W2002188480","https://openalex.org/W2113620787"],"abstract_inverted_index":{"Readability":[0],"and":[1,19,44,83,122],"accuracy":[2],"are":[3],"two":[4],"important":[5,81],"features":[6,33,82],"of":[7,47,58,108],"any":[8],"good":[9],"classifier.":[10],"For":[11],"reasons":[12],"such":[13],"as":[14],"acceptable":[15],"accuracy,":[16],"rapid":[17],"training":[18,42],"high":[20,56],"interpretability,":[21],"associative":[22],"classifiers":[23],"have":[24],"recently":[25],"been":[26],"used":[27],"in":[28,38,103,120,123],"many":[29],"categorization":[30],"tasks.":[31],"Although":[32],"could":[34],"be":[35],"very":[36],"useful":[37],"text":[39,59,69],"classification,":[40],"both":[41,119],"time":[43],"the":[45,55,100,106],"number":[46],"produced":[48],"rules":[49],"will":[50],"increase":[51],"significantly":[52],"owing":[53],"to":[54,79,91],"dimensionality":[57],"documents.":[60],"In":[61],"this":[62,93],"paper":[63],"an":[64],"association":[65],"classification":[66,70,111],"algorithm":[67,102],"for":[68],"is":[71],"proposed":[72,101],"that":[73,114],"includes":[74],"a":[75,84],"feature":[76],"selection":[77],"phase":[78,86],"select":[80],"clustering":[85],"based":[87],"on":[88],"class":[89],"labels":[90],"tackle":[92],"shortcoming.":[94],"The":[95],"experimental":[96],"results":[97,107],"from":[98],"applying":[99],"comparison":[104],"with":[105],"selected":[109],"well-known":[110],"algorithms":[112],"show":[113],"our":[115],"approach":[116],"outperforms":[117],"others":[118],"efficiency":[121],"performance.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}