{"id":"https://openalex.org/W2018079881","doi":"https://doi.org/10.2498/cit.1001770","title":"Arabic Text Classification Framework Based on Latent Dirichlet Allocation","display_name":"Arabic Text Classification Framework Based on Latent Dirichlet Allocation","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2018079881","doi":"https://doi.org/10.2498/cit.1001770","mag":"2018079881"},"language":"en","primary_location":{"id":"doi:10.2498/cit.1001770","is_oa":true,"landing_page_url":"https://doi.org/10.2498/cit.1001770","pdf_url":"http://cit.fer.hr/index.php/CIT/article/download/1770/1534","source":{"id":"https://openalex.org/S98565333","display_name":"Journal of Computing and Information Technology","issn_l":"1330-1136","issn":["1330-1136","1846-3908"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310314807","host_organization_name":"Faculty of Electrical Engineering and Computing, University of Zagreb","host_organization_lineage":["https://openalex.org/P4310314807"],"host_organization_lineage_names":["Faculty of Electrical Engineering and Computing, University of Zagreb"],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computing and Information Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://cit.fer.hr/index.php/CIT/article/download/1770/1534","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022321580","display_name":"Mounir Zrigui","orcid":"https://orcid.org/0000-0002-4199-8925"},"institutions":[{"id":"https://openalex.org/I166928557","display_name":"University of Monastir","ror":"https://ror.org/00nhtcg76","country_code":"TN","type":"education","lineage":["https://openalex.org/I166928557"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Mounir Zrigui","raw_affiliation_strings":["LaTICE Laboratory (Research Unit of Monastir ), University of Monastir, Tunisia"],"affiliations":[{"raw_affiliation_string":"LaTICE Laboratory (Research Unit of Monastir ), University of Monastir, Tunisia","institution_ids":["https://openalex.org/I166928557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007237930","display_name":"Rami Ayadi","orcid":null},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Rami Ayadi","raw_affiliation_strings":["Faculty of Economics and Management, University of Sfax, Tunisia","Faculty of Economics and Management - University of Sfax - Tunisia"],"affiliations":[{"raw_affiliation_string":"Faculty of Economics and Management, University of Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]},{"raw_affiliation_string":"Faculty of Economics and Management - University of Sfax - Tunisia","institution_ids":["https://openalex.org/I142899784"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011591110","display_name":"Mourad Mars","orcid":"https://orcid.org/0000-0003-0321-8470"},"institutions":[{"id":"https://openalex.org/I36085230","display_name":"Universit\u00e9 Stendhal \u2013 Grenoble 3","ror":"https://ror.org/03yppfm65","country_code":"FR","type":"education","lineage":["https://openalex.org/I36085230","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mourad Mars","raw_affiliation_strings":["Stendhal University, Grenoble, France","Stendhal University, Grenoble, France#TAB#"],"affiliations":[{"raw_affiliation_string":"Stendhal University, Grenoble, France","institution_ids":["https://openalex.org/I36085230"]},{"raw_affiliation_string":"Stendhal University, Grenoble, France#TAB#","institution_ids":["https://openalex.org/I36085230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061535304","display_name":"Mohsen Maraoui","orcid":"https://orcid.org/0000-0001-6598-7465"},"institutions":[{"id":"https://openalex.org/I166928557","display_name":"University of Monastir","ror":"https://ror.org/00nhtcg76","country_code":"TN","type":"education","lineage":["https://openalex.org/I166928557"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Mohsen Maraoui","raw_affiliation_strings":["University of Monastir, Tunisia"],"affiliations":[{"raw_affiliation_string":"University of Monastir, Tunisia","institution_ids":["https://openalex.org/I166928557"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022321580"],"corresponding_institution_ids":["https://openalex.org/I166928557"],"apc_list":{"value":450,"currency":"EUR","value_usd":485},"apc_paid":{"value":450,"currency":"EUR","value_usd":485},"fwci":3.9791,"has_fulltext":true,"cited_by_count":52,"citation_normalized_percentile":{"value":0.93572322,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"20","issue":"2","first_page":null,"last_page":null},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9925000071525574,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9915000200271606,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8954760432243347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8165265321731567},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6475057005882263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6415526270866394},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5519999265670776},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5400415658950806},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5077201128005981},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.4989945888519287},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.482856810092926},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.4635241627693176},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.46228861808776855},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4605485796928406},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45592808723449707},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4100194573402405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3597460687160492},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11828240752220154},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09305745363235474}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8954760432243347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165265321731567},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6475057005882263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6415526270866394},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5519999265670776},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5400415658950806},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5077201128005981},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.4989945888519287},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.482856810092926},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.4635241627693176},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.46228861808776855},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4605485796928406},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45592808723449707},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4100194573402405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3597460687160492},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11828240752220154},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09305745363235474},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.2498/cit.1001770","is_oa":true,"landing_page_url":"https://doi.org/10.2498/cit.1001770","pdf_url":"http://cit.fer.hr/index.php/CIT/article/download/1770/1534","source":{"id":"https://openalex.org/S98565333","display_name":"Journal of Computing and Information Technology","issn_l":"1330-1136","issn":["1330-1136","1846-3908"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310314807","host_organization_name":"Faculty of Electrical Engineering and Computing, University of Zagreb","host_organization_lineage":["https://openalex.org/P4310314807"],"host_organization_lineage_names":["Faculty of Electrical Engineering and Computing, University of Zagreb"],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computing and Information Technology","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.453.2334","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.453.2334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hrcak.srce.hr/file/126774/","raw_type":"text"},{"id":"pmh:oai:hrcak.srce.hr:85083","is_oa":true,"landing_page_url":"http://hrcak.srce.hr/85083","pdf_url":null,"source":{"id":"https://openalex.org/S4306400071","display_name":"University of Zagreb University Computing Centre (SRCE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I181343428","host_organization_name":"University of Zagreb","host_organization_lineage":["https://openalex.org/I181343428"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of computing and information technology","raw_type":"text"}],"best_oa_location":{"id":"doi:10.2498/cit.1001770","is_oa":true,"landing_page_url":"https://doi.org/10.2498/cit.1001770","pdf_url":"http://cit.fer.hr/index.php/CIT/article/download/1770/1534","source":{"id":"https://openalex.org/S98565333","display_name":"Journal of Computing and Information Technology","issn_l":"1330-1136","issn":["1330-1136","1846-3908"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310314807","host_organization_name":"Faculty of Electrical Engineering and Computing, University of Zagreb","host_organization_lineage":["https://openalex.org/P4310314807"],"host_organization_lineage_names":["Faculty of Electrical Engineering and Computing, University of Zagreb"],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computing and Information Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2018079881.pdf","grobid_xml":"https://content.openalex.org/works/W2018079881.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W35916491","https://openalex.org/W58431277","https://openalex.org/W101205528","https://openalex.org/W125310878","https://openalex.org/W154599901","https://openalex.org/W1576520375","https://openalex.org/W1586413166","https://openalex.org/W1660390307","https://openalex.org/W1880262756","https://openalex.org/W1966689924","https://openalex.org/W1979663147","https://openalex.org/W1984545377","https://openalex.org/W1996824467","https://openalex.org/W2077679384","https://openalex.org/W2088877638","https://openalex.org/W2091785715","https://openalex.org/W2106090053","https://openalex.org/W2109523953","https://openalex.org/W2110882072","https://openalex.org/W2112050062","https://openalex.org/W2116296392","https://openalex.org/W2148603752","https://openalex.org/W2149684865","https://openalex.org/W2165612380","https://openalex.org/W2166030254","https://openalex.org/W2171444767","https://openalex.org/W2364882444","https://openalex.org/W2395599974","https://openalex.org/W2989233272","https://openalex.org/W3144970731","https://openalex.org/W4254031464","https://openalex.org/W6607955601","https://openalex.org/W6635104619"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W3005513013","https://openalex.org/W2207653751","https://openalex.org/W2891616219","https://openalex.org/W2796920963","https://openalex.org/W3204672119"],"abstract_inverted_index":{"In":[0,42],"this":[1,43,75],"paper,":[2],"we":[3],"present":[4],"a":[5,49,78,106],"new":[6],"algorithm":[7,149],"based":[8],"on":[9,116],"the":[10,16,23,90,117,146],"LDA":[11,82],"(Latent":[12],"Dirichlet":[13],"Allocation)":[14],"and":[15,68,134,164],"Support":[17],"Vector":[18,32],"Machine":[19],"(SVM)":[20],"used":[21,137],"in":[22,38,64,74],"classification":[24,159],"of":[25,51,98,109,119,129],"Arabic":[26,130,157],"texts.":[27,131],"Current":[28],"research":[29],"usually":[30],"adopts":[31,77],"Space":[33],"Model":[34],"to":[35,138,152],"represent":[36],"documents":[37],"Text":[39],"Classification":[40],"applications.":[41],"way,":[44],"document":[45],"is":[46,103,114,150],"coded":[47],"as":[48,84],"vector":[50],"words;":[52],"n-grams.":[53],"These":[54],"features":[55],"cannot":[56],"indicate":[57],"semantic":[58,69],"or":[59],"textual":[60],"content;":[61],"it":[62],"results":[63,143],"huge":[65],"feature":[66],"space":[67],"loss.":[70],"The":[71,142],"proposed":[72,147],"model":[73,83],"work":[76],"\u201ctopics\u201d":[79],"sampled":[80],"by":[81,105],"text":[85,113,158],"features.":[86],"It":[87],"effectively":[88],"avoids":[89],"above":[91],"problems.":[92],"We":[93],"extracted":[94],"significant":[95],"themes":[96],"(topics)":[97],"all":[99],"texts,":[100],"each":[101,112],"theme":[102],"described":[104],"particular":[107],"distribution":[108],"descriptors,":[110],"then":[111],"represented":[115],"vectors":[118],"these":[120],"topics.":[121],"Experiments":[122],"are":[123,136],"conducted":[124],"using":[125],"an":[126],"in-house":[127],"corpus":[128],"Precision,":[132],"recall":[133],"F-measure":[135],"quantify":[139],"categorization":[140],"effectiveness.":[141],"show":[144],"that":[145],"LDA-SVM":[148],"able":[151],"achieve":[153],"high":[154],"effectiveness":[155],"for":[156],"task":[160],"(Macro-averaged":[161],"F1":[162,166],"88.1%":[163],"Micro-averaged":[165],"91.4%).":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
