{"id":"https://openalex.org/W2169206507","doi":"https://doi.org/10.1145/1242572.1242635","title":"Extraction and classification of dense communities in the web","display_name":"Extraction and classification of dense communities in the web","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W2169206507","doi":"https://doi.org/10.1145/1242572.1242635","mag":"2169206507"},"language":"en","primary_location":{"id":"doi:10.1145/1242572.1242635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://puma.isti.cnr.it/dfdownloadnew.php?ident=cnr.iit/cnr.iit/2006-TR-09","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076354637","display_name":"Yon Dourisboure","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130157","display_name":"Institute of Informatics and Telematics","ror":"https://ror.org/02gdcn153","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Yon Dourisboure","raw_affiliation_strings":["IIT-CNR, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"IIT-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I4210130157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033343264","display_name":"Filippo Geraci","orcid":"https://orcid.org/0000-0001-6993-6761"},"institutions":[{"id":"https://openalex.org/I4210130157","display_name":"Institute of Informatics and Telematics","ror":"https://ror.org/02gdcn153","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Filippo Geraci","raw_affiliation_strings":["IIT-CNR, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"IIT-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I4210130157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028551838","display_name":"Marco Pellegrini","orcid":"https://orcid.org/0000-0003-3151-9481"},"institutions":[{"id":"https://openalex.org/I4210130157","display_name":"Institute of Informatics and Telematics","ror":"https://ror.org/02gdcn153","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Pellegrini","raw_affiliation_strings":["IIT-CNR, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"IIT-CNR, Pisa, Italy","institution_ids":["https://openalex.org/I4210130157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076354637"],"corresponding_institution_ids":["https://openalex.org/I4210130157"],"apc_list":null,"apc_paid":null,"fwci":7.8363,"has_fulltext":false,"cited_by_count":204,"citation_normalized_percentile":{"value":0.98341359,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"461","last_page":"470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7454227805137634},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5784451365470886},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5257863998413086},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4949635863304138},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4316384792327881},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4288051128387451},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.41772234439849854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34125185012817383},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3176153898239136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1722579002380371}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454227805137634},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5784451365470886},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5257863998413086},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4949635863304138},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4316384792327881},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4288051128387451},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.41772234439849854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34125185012817383},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3176153898239136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1722579002380371}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1242572.1242635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.112.7509","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.112.7509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iit.cnr.it/staff/marco.pellegrini/papiri/www015-pellegrini.pdf","raw_type":"text"},{"id":"pmh:oai:pumaoai.isti.cnr.it:cnr.iit/cnr.iit/2006-TR-09","is_oa":true,"landing_page_url":"http://puma.isti.cnr.it/dfdownloadnew.php?ident=cnr.iit/cnr.iit/2006-TR-09","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Technical report, 2006.","raw_type":"info:eu-repo/semantics/report"}],"best_oa_location":{"id":"pmh:oai:pumaoai.isti.cnr.it:cnr.iit/cnr.iit/2006-TR-09","is_oa":true,"landing_page_url":"http://puma.isti.cnr.it/dfdownloadnew.php?ident=cnr.iit/cnr.iit/2006-TR-09","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Technical report, 2006.","raw_type":"info:eu-repo/semantics/report"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522854417","https://openalex.org/W1552319112","https://openalex.org/W1586169687","https://openalex.org/W1586552957","https://openalex.org/W1594746766","https://openalex.org/W1604983895","https://openalex.org/W1937062790","https://openalex.org/W1971421925","https://openalex.org/W1977001629","https://openalex.org/W1984374364","https://openalex.org/W1994727615","https://openalex.org/W2000273502","https://openalex.org/W2011918288","https://openalex.org/W2020423193","https://openalex.org/W2034543148","https://openalex.org/W2036836182","https://openalex.org/W2072802070","https://openalex.org/W2080676333","https://openalex.org/W2081193615","https://openalex.org/W2081254453","https://openalex.org/W2087303323","https://openalex.org/W2089199911","https://openalex.org/W2102931907","https://openalex.org/W2104890789","https://openalex.org/W2120407371","https://openalex.org/W2134122907","https://openalex.org/W2139148100","https://openalex.org/W2148606196","https://openalex.org/W2151626491","https://openalex.org/W2152565070","https://openalex.org/W2155048531","https://openalex.org/W2169270715","https://openalex.org/W2171396134","https://openalex.org/W2175110005","https://openalex.org/W2241797981","https://openalex.org/W2293888960","https://openalex.org/W2912431181","https://openalex.org/W6640619417","https://openalex.org/W6682678078"],"related_works":["https://openalex.org/W2183707945","https://openalex.org/W2351714940","https://openalex.org/W2187012497","https://openalex.org/W2326648636","https://openalex.org/W3174726539","https://openalex.org/W2182629206","https://openalex.org/W2945931694","https://openalex.org/W2356598865","https://openalex.org/W2330648582","https://openalex.org/W4385950365"],"abstract_inverted_index":{"The":[0,102,146],"World":[1],"Wide":[2],"Web":[3],"(WWW)":[4],"is":[5,22,58,107,155,185,202],"rapidly":[6],"becoming":[7],"important":[8],"for":[9,14,28,112,189,207],"society":[10],"as":[11],"a":[12,23,56,59,65,83,108,192],"medium":[13],"sharing":[15],"data,":[16],"information":[17],"and":[18,20,32,48,95,143,165,179,254],"services,":[19],"there":[21],"growing":[24],"interest":[25],"in":[26,35,51,74,117,151,162,246],"tools":[27],"understanding":[29],"collective":[30],"behaviors":[31],"emerging":[33],"phenomena":[34],"the":[36,44,52,75,80,88,100,134,163,177,182,217,221,224,243,247],"WWW.":[37],"In":[38],"this":[39],"paper":[40],"we":[41],"focus":[42],"on":[43,124,127],"problem":[45],"of":[46,61,82,87,99,104,133,148,169,181,191,209,216,228,232],"searching":[47],"classifying":[49],"communities":[50,70,161,190,208,230,244],"web.":[53],"Loosely":[54],"speaking":[55],"community":[57],"group":[60,257],"pages":[62,92],"related":[63],"to":[64,140,187],"common":[66],"interest.":[67],"More":[68],"formally":[69],"have":[71],"been":[72],"associated":[73],"computer":[76],"science":[77],"literature":[78],"with":[79,176,212],"existence":[81],"locally":[84],"dense":[85,115,153,229],"sub-graph":[86],"web-graph":[89,164,248],"(where":[90],"web":[91,135],"are":[93,97,171],"nodes":[94,142,194,211],"hyper-links":[96],"arcs":[98,218],"web-graph).":[101],"core":[103],"our":[105,122,149,237],"contribution":[106],"new":[109],"scalable":[110],"algorithm":[111,123,150,225],"finding":[113,152],"relatively":[114],"subgraphs":[116,154],"massive":[118],"graphs.":[119],"We":[120,235],"apply":[121],"web-graphs":[125],"built":[126],"three":[128],"publicly":[129],"available":[130],"large":[131],"crawls":[132],"(with":[136],"raw":[137],"sizes":[138],"up":[139],"120M":[141],"1G":[144],"arcs).":[145],"effectiveness":[147],"demonstrated":[156],"experimentally":[157],"by":[158,241,252,258],"embedding":[159],"artificial":[160],"counting":[166],"how":[167],"many":[168],"these":[170],"blindly":[172],"found.":[173],"Effectiveness":[174],"increases":[175],"size":[178],"density":[180,213],"communities:":[183],"it":[184],"close":[186],"100%":[188],"thirty":[193],"or":[195],"more":[196],"(even":[197],"at":[198],"low":[199],"density).":[200],"It":[201],"still":[203],"about":[204],"80%":[205],"even":[206],"twenty":[210],"over":[214],"50%":[215],"present.":[219],"At":[220],"lower":[222],"extremes":[223],"catches":[226],"35%":[227],"made":[231],"ten":[233],"nodes.":[234],"complete":[236],"Community":[238],"Watch":[239],"system":[240],"clustering":[242],"found":[245],"into":[249],"homogeneous":[250],"groups":[251],"topic":[253],"labelling":[255],"each":[256],"representative":[259],"keywords.":[260]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":14}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
