{"id":"https://openalex.org/W3161732143","doi":"https://doi.org/10.1109/csicc52343.2021.9420602","title":"A Semantic-based Feature Extraction Method Using Categorical Clustering for Persian Document Classification","display_name":"A Semantic-based Feature Extraction Method Using Categorical Clustering for Persian Document Classification","publication_year":2021,"publication_date":"2021-03-03","ids":{"openalex":"https://openalex.org/W3161732143","doi":"https://doi.org/10.1109/csicc52343.2021.9420602","mag":"3161732143"},"language":"en","primary_location":{"id":"doi:10.1109/csicc52343.2021.9420602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csicc52343.2021.9420602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","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/A5060659311","display_name":"Saeedeh Davoudi","orcid":null},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Saeedeh Davoudi","raw_affiliation_strings":["University of Tehran,School of Engineering Science, College of Engineering,Tehran,Iran","School of Engineering Science, College of Engineering, University of Tehran, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran,School of Engineering Science, College of Engineering,Tehran,Iran","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"School of Engineering Science, College of Engineering, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026428383","display_name":"Sayeh Mirzaei","orcid":"https://orcid.org/0000-0003-1174-2280"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Sayeh Mirzaei","raw_affiliation_strings":["University of Tehran,School of Engineering Science, College of Engineering,Tehran,Iran","School of Engineering Science, College of Engineering, University of Tehran, Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tehran,School of Engineering Science, College of Engineering,Tehran,Iran","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"School of Engineering Science, College of Engineering, University of Tehran, Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I23946033"],"apc_list":null,"apc_paid":null,"fwci":0.6995,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75732162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9961000084877014,"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":0.9959999918937683,"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/word2vec","display_name":"Word2vec","score":0.9368166923522949},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8219242095947266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6827850341796875},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6095196008682251},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.6088420748710632},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5193868279457092},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.4907906949520111},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.4374876320362091},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4185880422592163},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4126593768596649},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3975656032562256},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36960214376449585},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35863929986953735},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34179186820983887},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29621827602386475},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.16462305188179016},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08886665105819702}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.9368166923522949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8219242095947266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6827850341796875},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6095196008682251},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.6088420748710632},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5193868279457092},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.4907906949520111},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.4374876320362091},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4185880422592163},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4126593768596649},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3975656032562256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36960214376449585},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35863929986953735},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34179186820983887},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29621827602386475},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.16462305188179016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08886665105819702},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/csicc52343.2021.9420602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csicc52343.2021.9420602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 26th International Computer Conference, Computer Society of Iran (CSICC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6100000143051147,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W40563694","https://openalex.org/W71931951","https://openalex.org/W143162004","https://openalex.org/W168564468","https://openalex.org/W1569375842","https://openalex.org/W1614298861","https://openalex.org/W2026306693","https://openalex.org/W2101234009","https://openalex.org/W2118020653","https://openalex.org/W2529435478","https://openalex.org/W2565001422","https://openalex.org/W2591272477","https://openalex.org/W2594674086","https://openalex.org/W2744280098","https://openalex.org/W2851904645","https://openalex.org/W2883730939","https://openalex.org/W2950577311","https://openalex.org/W3032087714","https://openalex.org/W4237359383","https://openalex.org/W6602936794","https://openalex.org/W6606906144","https://openalex.org/W6636510571","https://openalex.org/W6675354045","https://openalex.org/W6774896011"],"related_works":["https://openalex.org/W2903145235","https://openalex.org/W3003606604","https://openalex.org/W4226211987","https://openalex.org/W3040974839","https://openalex.org/W2574070988","https://openalex.org/W2795129682","https://openalex.org/W2913738019","https://openalex.org/W2747336051","https://openalex.org/W2580878117","https://openalex.org/W2208234687"],"abstract_inverted_index":{"Natural":[0],"Language":[1],"Processing":[2],"(NLP)":[3],"is":[4,31,59],"one":[5],"of":[6,10,18,29,35,56,83,114,125,130,157,182],"the":[7,25,81,107,111,140,155,158,179],"promising":[8],"fields":[9,43],"artificial":[11],"intelligence.":[12],"In":[13,62],"recent":[14],"decades,":[15],"high":[16],"volume":[17],"text":[19,57],"data":[20,30],"has":[21],"been":[22],"generated":[23],"through":[24],"Internet.":[26],"This":[27],"kind":[28],"a":[32,74],"valuable":[33],"source":[34],"information":[36,46],"which":[37],"can":[38],"be":[39],"used":[40],"in":[41,175,178,189],"various":[42],"such":[44],"as":[45],"retrieval,":[47],"search":[48],"engines,":[49],"recommender":[50],"systems,":[51],"etc.":[52],"One":[53],"practical":[54],"task":[55],"mining":[58],"document":[60,70],"classification.":[61,71],"this":[63],"paper,":[64],"we":[65,105],"mainly":[66],"focus":[67],"on":[68],"Persian":[69],"We":[72,96,121,138],"introduce":[73],"new":[75,172],"feature":[76],"extraction":[77],"approach":[78,100,160,173],"derived":[79],"from":[80],"combination":[82],"K-means":[84],"clustering":[85],"and":[86,92,148,168,185,193],"Word2Vec":[87,108,169,194],"to":[88,134,144,153],"acquire":[89],"semantically":[90],"relevant":[91],"discriminant":[93],"word":[94,112,142],"representations.":[95],"call":[97],"our":[98,136],"proposed":[99,159],"CC-Word2Vec":[101],"(Categorical":[102],"Clustering-Word2Vec)":[103],"since":[104],"retrain":[106],"model":[109],"using":[110],"clusters":[113],"each":[115],"category":[116],"obtained":[117,180],"by":[118],"K-Means":[119],"algorithm.":[120],"use":[122],"200":[123],"documents":[124],"5":[126],"most":[127],"frequent":[128],"categories":[129],"Hamshahri":[131],"news":[132],"dataset":[133],"evaluate":[135],"method.":[137],"pass":[139],"extracted":[141],"vectors":[143],"Multi-Layer":[145,186],"Perceptron":[146,187],"(MLP)":[147],"Gradient":[149,183],"Boosting":[150,184],"(GB)":[151],"classifiers":[152],"compare":[154],"performance":[156],"with":[161,191],"Term":[162],"Frequency":[163,166],"Inverse":[164],"Document":[165],"(TF-IDF)":[167],"methods.":[170],"Our":[171],"resulted":[174],"an":[176],"improvement":[177],"accuracy":[181],"models":[188],"comparison":[190],"TF-IDF":[192],"techniques.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}