{"id":"https://openalex.org/W2049582451","doi":"https://doi.org/10.1145/2631775.2631795","title":"Scalable, generic, and adaptive systems for focused crawling","display_name":"Scalable, generic, and adaptive systems for focused crawling","publication_year":2014,"publication_date":"2014-08-29","ids":{"openalex":"https://openalex.org/W2049582451","doi":"https://doi.org/10.1145/2631775.2631795","mag":"2049582451"},"language":"en","primary_location":{"id":"doi:10.1145/2631775.2631795","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2631775.2631795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM conference on Hypertext and social media","raw_type":"proceedings-article"},"type":"preprint","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/A5053259203","display_name":"Georges Gouriten","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Georges Gouriten","raw_affiliation_strings":["Institut Mines-T\u00e9l\u00e9com; T\u00e9l\u00e9com ParisTech; CNRS LTCI, Paris, France"],"affiliations":[{"raw_affiliation_string":"Institut Mines-T\u00e9l\u00e9com; T\u00e9l\u00e9com ParisTech; CNRS LTCI, Paris, France","institution_ids":["https://openalex.org/I205703379","https://openalex.org/I12356871","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035115589","display_name":"Silviu Maniu","orcid":"https://orcid.org/0000-0002-8623-1533"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Silviu Maniu","raw_affiliation_strings":["University of Hong Kong, Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035414136","display_name":"Pierre Senellart","orcid":"https://orcid.org/0000-0002-7909-5369"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre Senellart","raw_affiliation_strings":["Institut Mines-T\u00e9l\u00e9com; T\u00e9l\u00e9com ParisTech; CNRS LTCI, Paris, France"],"affiliations":[{"raw_affiliation_string":"Institut Mines-T\u00e9l\u00e9com; T\u00e9l\u00e9com ParisTech; CNRS LTCI, Paris, France","institution_ids":["https://openalex.org/I205703379","https://openalex.org/I12356871","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053259203"],"corresponding_institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I205703379","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":7.3625,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.96788647,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9825000166893005,"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/crawling","display_name":"Crawling","score":0.8605055809020996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8225409984588623},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7133044600486755},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5752490162849426},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5355989933013916},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.4743427336215973},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4387558400630951},{"id":"https://openalex.org/keywords/social-graph","display_name":"Social graph","score":0.4383571147918701},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43727922439575195},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41024211049079895},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3460225462913513},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.27341389656066895},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10179933905601501},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09319135546684265}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8605055809020996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8225409984588623},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7133044600486755},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5752490162849426},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5355989933013916},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.4743427336215973},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4387558400630951},{"id":"https://openalex.org/C2777522414","wikidata":"https://www.wikidata.org/wiki/Q648457","display_name":"Social graph","level":3,"score":0.4383571147918701},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43727922439575195},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41024211049079895},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3460225462913513},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.27341389656066895},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10179933905601501},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09319135546684265},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2631775.2631795","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2631775.2631795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM conference on Hypertext and social media","raw_type":"proceedings-article"},{"id":"pmh:oai:hub.hku.hk:10722/201108","is_oa":false,"landing_page_url":"http://hdl.handle.net/10722/201108","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference_Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G5983552075","display_name":null,"funder_award_id":"X-Data","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320318270","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W173995639","https://openalex.org/W1485536830","https://openalex.org/W1489992655","https://openalex.org/W2001832505","https://openalex.org/W2010505009","https://openalex.org/W2017224880","https://openalex.org/W2017726337","https://openalex.org/W2053634345","https://openalex.org/W2071102467","https://openalex.org/W2081128931","https://openalex.org/W2090275183","https://openalex.org/W2097704339","https://openalex.org/W2098275949","https://openalex.org/W2102942431","https://openalex.org/W2112056172","https://openalex.org/W2118356300","https://openalex.org/W2124673015","https://openalex.org/W2146968241","https://openalex.org/W2151809999","https://openalex.org/W2158601853","https://openalex.org/W2167489871","https://openalex.org/W2795857897","https://openalex.org/W2997776631","https://openalex.org/W6678701036"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2089702591","https://openalex.org/W2304841839"],"abstract_inverted_index":{"Focused":[0],"crawling":[1,130],"is":[2,85,97,123,169],"the":[3,14,37,48,67,79,95,100,104,152,157,167],"process":[4],"of":[5,13,50,82,103,128,136,159],"exploring":[6],"a":[7,18,28,34,41,55,64,70,133,142],"graph":[8,15,65],"iteratively,":[9],"focusing":[10],"on":[11,32],"parts":[12],"relevant":[16,153],"to":[17,39,98,124,132,148],"given":[19],"topic.":[20],"It":[21],"occurs":[22],"in":[23],"many":[24],"situations":[25],"such":[26],"as":[27],"company":[29],"collecting":[30],"data":[31],"competition,":[33],"journalist":[35],"surfing":[36],"Web":[38,68],"investigate":[40],"political":[42],"scandal,":[43],"or":[44,69],"an":[45,126,161],"archivist":[46],"recording":[47],"activity":[49],"influential":[51],"Twitter":[52],"users":[53,62],"during":[54],"presidential":[56],"election.":[57],"In":[58,107],"all":[59,166],"these":[60],"applications,":[61],"explore":[63],"(e.g.,":[66],"social":[71],"network),":[72],"nodes":[73,88],"are":[74,89],"discovered":[75],"one":[76],"by":[77],"one,":[78],"total":[80,101],"number":[81],"exploration":[83],"steps":[84],"constrained,":[86],"some":[87],"more":[90],"valuable":[91],"than":[92],"others,":[93],"and":[94,114,150],"objective":[96],"maximize":[99],"value":[102],"crawled":[105],"subgraph.":[106],"this":[108],"article,":[109],"we":[110],"introduce":[111],"scalable,":[112],"generic,":[113],"adaptive":[115],"systems":[116],"for":[117],"focused":[118,129],"crawling.":[119],"Our":[120],"first":[121],"effort":[122],"define":[125],"abstraction":[127],"applicable":[131],"large":[134],"domain":[135],"real-world":[137],"scenarios.":[138],"We":[139,155],"then":[140],"propose":[141],"generic":[143],"algorithm,":[144],"which":[145],"allows":[146],"us":[147],"identify":[149],"optimize":[151],"subsystems.":[154],"prove":[156],"intractability":[158],"finding":[160],"optimal":[162],"exploration,":[163],"even":[164],"when":[165],"information":[168],"available.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
