{"id":"https://openalex.org/W2171565655","doi":"https://doi.org/10.1109/icdim.2010.5664660","title":"An approach in web content mining for clustering web pages","display_name":"An approach in web content mining for clustering web pages","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2171565655","doi":"https://doi.org/10.1109/icdim.2010.5664660","mag":"2171565655"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2010.5664660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2010.5664660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Fifth International Conference on Digital Information Management (ICDIM)","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/A5072766724","display_name":"Roohollah Etemadi","orcid":"https://orcid.org/0000-0002-6099-0558"},"institutions":[{"id":"https://openalex.org/I1293555014","display_name":"Islamic Azad University of Tabriz","ror":"https://ror.org/04hnf9a51","country_code":"IR","type":"education","lineage":["https://openalex.org/I110525433","https://openalex.org/I1293555014"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"R. Etemadi","raw_affiliation_strings":["Department of Electrical and computer engineering, Islamic Azad University, Tabriz, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and computer engineering, Islamic Azad University, Tabriz, Iran","institution_ids":["https://openalex.org/I1293555014"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112980980","display_name":"Norwati Mustapha Morteza Ghorbani Moghaddam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116604","display_name":"Ilam University","ror":"https://ror.org/01r277z15","country_code":"IR","type":"education","lineage":["https://openalex.org/I4210116604"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"N. Moghaddam","raw_affiliation_strings":["Department of Electrical engineering and computer engineering, Tarbiat Moalem University, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Electrical engineering and computer engineering, Tarbiat Moalem University, Tehran, Iran","institution_ids":["https://openalex.org/I4210116604"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072766724"],"corresponding_institution_ids":["https://openalex.org/I1293555014"],"apc_list":null,"apc_paid":null,"fwci":1.3874,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8895847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"7","issue":null,"first_page":"279","last_page":"284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.996399998664856,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.996399998664856,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9901999831199646,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9775999784469604,"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":0.7866650819778442},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7526394724845886},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7426266670227051},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.7230150699615479},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6213921308517456},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5408101677894592},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49826884269714355},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4956003427505493},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.4109652042388916},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4104887843132019},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.30125606060028076},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.2551429867744446},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20294761657714844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7866650819778442},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7526394724845886},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7426266670227051},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.7230150699615479},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6213921308517456},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5408101677894592},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49826884269714355},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4956003427505493},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.4109652042388916},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4104887843132019},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.30125606060028076},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.2551429867744446},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20294761657714844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdim.2010.5664660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2010.5664660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Fifth International Conference on Digital Information Management (ICDIM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W88864901","https://openalex.org/W95719993","https://openalex.org/W203085507","https://openalex.org/W208128215","https://openalex.org/W1664762403","https://openalex.org/W1966695765","https://openalex.org/W1981697855","https://openalex.org/W1989533365","https://openalex.org/W1989993068","https://openalex.org/W1996764654","https://openalex.org/W2045584315","https://openalex.org/W2069206060","https://openalex.org/W2084132447","https://openalex.org/W2123509976","https://openalex.org/W2124924555","https://openalex.org/W2140190241","https://openalex.org/W2144599263","https://openalex.org/W2156644018","https://openalex.org/W2167403283","https://openalex.org/W2574091758","https://openalex.org/W3146003712","https://openalex.org/W3147179393","https://openalex.org/W4241122026","https://openalex.org/W4298266977","https://openalex.org/W6601904100"],"related_works":["https://openalex.org/W4381948805","https://openalex.org/W4214483597","https://openalex.org/W4220978606","https://openalex.org/W4220894110","https://openalex.org/W4388145912","https://openalex.org/W4286850906","https://openalex.org/W4313532769","https://openalex.org/W1437580529","https://openalex.org/W2307895033","https://openalex.org/W2376574812"],"abstract_inverted_index":{"Nowadays,":[0],"using":[1,97,168],"web":[2,30,49,67,88,185,204],"and":[3,83,90,96,105,131,137,157,164,187],"Internet":[4],"as":[5],"a":[6,59,94,98,140],"world":[7],"wide":[8],"information":[9],"system":[10,133],"faces":[11],"us":[12],"with":[13,118],"so":[14,45],"many":[15],"data.":[16],"In":[17,56],"this":[18,57,162],"direction,":[19],"the":[20,34,48,81,111,144,180,199],"necessity":[21],"of":[22,53,113,121,127,155,159,179,198],"accessing":[23],"some":[24,116],"tools":[25],"for":[26],"data":[27,40,71,142],"processing":[28,130],"in":[29,87,161,183,196],"level":[31],"which":[32],"helps":[33],"man":[35],"intelligently":[36],"to":[37,65,202],"transform":[38],"these":[39,54],"into":[41],"useful":[42],"knowledge":[43],"seems":[44],"important.":[46],"Clustering":[47],"pages":[50,68,117,186],"is":[51],"one":[52],"techniques.":[55],"paper,":[58],"new":[60,74,99],"algorithm":[61,75,146,181,192],"has":[62,76,147,165],"been":[63,77,135,148,166],"represented":[64,145,160,191],"cluster":[66],"based":[69,79],"on":[70,80],"content.":[72],"The":[73,171,190],"suggested":[78,114],"expressions":[82],"key":[84],"words":[85],"existed":[86],"pages,":[89],"their":[91,188],"bit":[92],"display":[93],"vector":[95],"similarity":[100,107,153],"criterion":[101],"obtained":[102,173],"from":[103,174],"Cosine":[104,156],"Jaccard":[106],"criterion.":[108],"To":[109],"evaluate":[110],"efficacy":[112],"algorithm,":[115],"five":[119],"subjects":[120],"software":[122],"engineering,":[123],"computerized":[124],"networks,":[125],"architecture":[126],"computer,":[128],"parallel":[129],"operating":[132],"have":[134],"investigated":[136],"after":[138],"preparing":[139],"suitable":[141],"bed":[143],"simulated":[149],"separately":[150],"through":[151],"two":[152],"criteria":[154],"that":[158],"pager":[163],"evaluated":[167],"Dunn":[169],"index.":[170],"results":[172],"simulation":[175],"show":[176],"high":[177],"efficiency":[178],"proposed":[182],"separating":[184],"clustering.":[189],"can":[193],"be":[194],"used":[195],"most":[197],"problems":[200],"related":[201],"clustering":[203],"pages.":[205]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
