{"id":"https://openalex.org/W60538693","doi":null,"title":"Using some web content mining techniques for Arabic text classification","display_name":"Using some web content mining techniques for Arabic text classification","publication_year":2009,"publication_date":"2009-11-01","ids":{"openalex":"https://openalex.org/W60538693","mag":"60538693"},"language":"en","primary_location":{"id":"mag:60538693","doi":null,"is_oa":false,"landing_page_url":"http://www.wseas.us/e-library/conferences/2009/baltimore/DNCOCO/DNCOCO-09.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5078467516","display_name":"Zakaria Suliman Zubi","orcid":"https://orcid.org/0000-0002-6062-1517","observed_orcids":["https://orcid.org/0000-0002-6062-1517"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zakaria Suliman Zubi","raw_affiliation_strings":["Computer Science Department, Faculty of Science, Al-Tahadi University, Sirt, Libya#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-6062-1517","affiliations":[{"raw_affiliation_string":"Computer Science Department, Faculty of Science, Al-Tahadi University, Sirt, Libya#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5078467516"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4277,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.82295269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0003000000142492354,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0003000000142492354,"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/arabic-text-classification","display_name":"Arabic text classification","score":0.9890000224113464},{"id":"https://openalex.org/keywords/web-content-mining","display_name":"web content mining","score":0.9929999709129333},{"id":"https://openalex.org/keywords/arabic-natural-language-processing","display_name":"Arabic language processing","score":0.5419999957084656},{"id":"https://openalex.org/keywords/phrase-segmentation","display_name":"phrase segmentation","score":0.7570000290870667},{"id":"https://openalex.org/keywords/k-nearest-neighbors","display_name":"k-nearest neighbors","score":0.9480000138282776},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.9620000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7901585102081299},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.7264274954795837},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6163469552993774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5300428867340088},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5074955821037292},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.49746397137641907},{"id":"https://openalex.org/C176775163","wikidata":"https://www.wikidata.org/wiki/Q5158396","display_name":"Concept mining","level":4,"score":0.4625069499015808},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.45793581008911133},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4368991255760193},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.42334115505218506},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.42042413353919983},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37867897748947144},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.33642858266830444},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.2696211338043213},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.255492240190506}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:60538693","doi":null,"is_oa":false,"landing_page_url":"http://www.wseas.us/e-library/conferences/2009/baltimore/DNCOCO/DNCOCO-09.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W78961616","https://openalex.org/W84280981","https://openalex.org/W125310878","https://openalex.org/W1482260847","https://openalex.org/W1512730339","https://openalex.org/W1520963883","https://openalex.org/W1539477445","https://openalex.org/W1554600341","https://openalex.org/W1576676390","https://openalex.org/W1586413166","https://openalex.org/W1594031697","https://openalex.org/W1596290048","https://openalex.org/W1606247040","https://openalex.org/W1971784203","https://openalex.org/W1978394996","https://openalex.org/W1984545377","https://openalex.org/W1988217119","https://openalex.org/W2005422315","https://openalex.org/W2019468486","https://openalex.org/W2049992327","https://openalex.org/W2050559027","https://openalex.org/W2076008912","https://openalex.org/W2077679384","https://openalex.org/W2103333826","https://openalex.org/W2118020653","https://openalex.org/W2126850915","https://openalex.org/W2140190241","https://openalex.org/W2149684865","https://openalex.org/W2160196229","https://openalex.org/W2163942188","https://openalex.org/W2402367090","https://openalex.org/W2963823794","https://openalex.org/W3085162807"],"related_works":["https://openalex.org/W7098860792","https://openalex.org/W2266803236","https://openalex.org/W2096794280","https://openalex.org/W4308610550","https://openalex.org/W1997377854","https://openalex.org/W4248563703","https://openalex.org/W2152318140","https://openalex.org/W34690091","https://openalex.org/W2067081262","https://openalex.org/W6977235990"],"abstract_inverted_index":{"With":[0],"the":[1,5,11,18,58,75,114,162,170,194,200,215,236,261,271,285,298],"massive":[2],"rise":[3],"in":[4,37,47,133,184,193,289],"volume":[6],"of":[7,35,70,154,159,181,230,256,297],"information":[8,54],"available":[9],"on":[10,219],"World":[12,59,76],"Wide":[13,60,77],"Web":[14,41,61,78,81],"these":[15,71],"days,":[16],"and":[17,95,118,198,209,223,269],"emergence":[19],"requirements":[20],"for":[21,161,169],"a":[22,32,44,144,152,157,178,185,228,279],"superior":[23],"technique":[24],"to":[25,57,62,73,104,109,129,165,176,196,226,234,259,277],"access":[26,74],"this":[27,99,290],"information,":[28],"there":[29],"has":[30],"been":[31],"strong":[33],"resurgence":[34],"interest":[36],"web":[38,106,124,238],"mining":[39,42,49,82,108,125],"research.":[40],"is":[43,258],"critical":[45],"issue":[46],"data":[48],"as":[50,52,90,143,156],"well":[51],"other":[53],"process":[55,164],"techniques":[56,191],"discover":[63],"useful":[64],"patterns.":[65],"People":[66],"can":[67,83],"take":[68],"advantage":[69],"patterns":[72],"more":[79],"efficiently.":[80],"be":[84,141,247],"divided":[85],"into":[86],"three":[87],"categories":[88],"such":[89],"content":[91,107],"mining,":[92,94],"usage":[93],"structure":[96],"mining.":[97],"In":[98],"paper":[100,291],"we":[101],"are":[102,202],"going":[103],"apply":[105,166],"extract":[110],"non-English":[111],"knowledge":[112],"from":[113],"web.\r\n\r\nWe":[115],"will":[116,140,150,246],"investigate":[117],"evaluate":[119],"some":[120,220],"common":[121],"methods;":[122],"using":[123],"systems":[126],"which":[127],"have":[128],"deal":[130],"with":[131],"issues":[132],"language-specific":[134],"text":[135,167,188,243],"processing.":[136],"Arabic":[137,242,249],"language-independent":[138],"algorithm":[139,149,173,195],"used":[142,175,192,266],"machine":[145],"learning":[146,163],"system.":[147,171,299],"The":[148,172,190,253,282],"use":[151],"set":[153,229],"features":[155,231],"vector":[158],"keywords":[160,233],"classification":[168,244],"usually":[174,217],"classify":[177],"various":[179],"number":[180],"documents":[182,201],"written":[183],"non":[186],"English":[187],"language.":[189],"categorize":[197],"classified":[199],"two":[203],"classifiers:":[204],"Classifier":[205,210,251],"K-Nearest":[206],"Neighbor":[207],"(CK-NN)":[208],"Naive":[211],"Bayes":[212],"(CNB).":[213],"However,":[214],"algorithms":[216],"depend":[218],"phrase":[221],"segmentation":[222],"extraction":[224],"programs":[225],"generate":[227],"or":[232],"represent":[235],"retrieved":[237],"documents.":[239],"A":[240],"proposed":[241],"system":[245],"called":[248],"Text":[250],"(ATC).":[252],"main":[254],"goal":[255],"ATC":[257,286],"compares":[260],"results":[262],"between":[263],"both":[264],"classifiers":[265],"(CKNN,":[267],"CNB)":[268],"select":[270],"best":[272],"average":[273],"accuracy":[274],"result":[275],"rates":[276],"start":[278],"retrieving":[280],"process.":[281],"theorem":[283],"behind":[284],"was":[287],"introduced":[288],"without":[292],"demonstrating":[293],"any":[294],"practical":[295],"views":[296]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}