{"id":"https://openalex.org/W2079615579","doi":"https://doi.org/10.1145/2492517.2500328","title":"An analyst-adaptive approach to focused crawlers","display_name":"An analyst-adaptive approach to focused crawlers","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2079615579","doi":"https://doi.org/10.1145/2492517.2500328","mag":"2079615579"},"language":"en","primary_location":{"id":"doi:10.1145/2492517.2500328","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2492517.2500328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","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/A5103049522","display_name":"Rodolfo Zunino","orcid":"https://orcid.org/0000-0002-2150-7076"},"institutions":[{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rodolfo Zunino","raw_affiliation_strings":["University of Genova, Genova, Italy","DITEN, University of Genova, Genoa, Italy#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Genova, Genova, Italy","institution_ids":["https://openalex.org/I83816512"]},{"raw_affiliation_string":"DITEN, University of Genova, Genoa, Italy#TAB#","institution_ids":["https://openalex.org/I83816512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075110204","display_name":"Federica Bisio","orcid":null},"institutions":[{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Federica Bisio","raw_affiliation_strings":["University of Genova, Genova, Italy","DITEN, University of Genova, Genoa, Italy#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Genova, Genova, Italy","institution_ids":["https://openalex.org/I83816512"]},{"raw_affiliation_string":"DITEN, University of Genova, Genoa, Italy#TAB#","institution_ids":["https://openalex.org/I83816512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013474152","display_name":"Chiara Peretti","orcid":null},"institutions":[{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Chiara Peretti","raw_affiliation_strings":["University of Genova, Genova, Italy","DITEN, University of Genova, Genoa, Italy#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Genova, Genova, Italy","institution_ids":["https://openalex.org/I83816512"]},{"raw_affiliation_string":"DITEN, University of Genova, Genoa, Italy#TAB#","institution_ids":["https://openalex.org/I83816512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046605897","display_name":"Roberto Surlinelli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Surlinelli","raw_affiliation_strings":["Polizia Postale e delle Comunicazioni, Genova, Italy","Comp. Liguria, Polizia Postale e delle Comun., Genoa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polizia Postale e delle Comunicazioni, Genova, Italy","institution_ids":[]},{"raw_affiliation_string":"Comp. Liguria, Polizia Postale e delle Comun., Genoa, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025860766","display_name":"Eugenio Scillia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eugenio Scillia","raw_affiliation_strings":["Polizia Postale e delle Comunicazioni, Genova, Italy","Comp. Liguria, Polizia Postale e delle Comun., Genoa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polizia Postale e delle Comunicazioni, Genova, Italy","institution_ids":[]},{"raw_affiliation_string":"Comp. Liguria, Polizia Postale e delle Comun., Genoa, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016114216","display_name":"Augusto Ottaviano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Augusto Ottaviano","raw_affiliation_strings":["Polizia Postale e delle Comunicazioni, Genova, Italy","Comp. Liguria, Polizia Postale e delle Comun., Genoa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polizia Postale e delle Comunicazioni, Genova, Italy","institution_ids":[]},{"raw_affiliation_string":"Comp. Liguria, Polizia Postale e delle Comun., Genoa, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037424313","display_name":"Fabio Sangiacomo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabio Sangiacomo","raw_affiliation_strings":["CyberLabs Srl, Garbagnate Milanese, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CyberLabs Srl, Garbagnate Milanese, Italy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5086,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.91588183,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1073","last_page":"1077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10260","display_name":"Software Engineering Research","score":0.9976999759674072,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8742033243179321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8371528387069702},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7562919855117798},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.6577851176261902},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6074539422988892},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5605618357658386},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.44937989115715027},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4238625168800354},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.40449780225753784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2597614526748657},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24628862738609314},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.19806569814682007},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.1571303904056549}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8742033243179321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371528387069702},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7562919855117798},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.6577851176261902},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6074539422988892},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5605618357658386},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.44937989115715027},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4238625168800354},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.40449780225753784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2597614526748657},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24628862738609314},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.19806569814682007},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.1571303904056549},{"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/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2492517.2500328","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2492517.2500328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unige.it:11567/694168","is_oa":false,"landing_page_url":"http://hdl.handle.net/11567/694168","pdf_url":null,"source":{"id":"https://openalex.org/S4377196291","display_name":"CINECA IRIS Institutial Research Information System (University of Genoa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83816512","host_organization_name":"University of Genoa","host_organization_lineage":["https://openalex.org/I83816512"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W173995639","https://openalex.org/W1489992655","https://openalex.org/W1507987782","https://openalex.org/W1585358604","https://openalex.org/W1596967103","https://openalex.org/W1625255723","https://openalex.org/W1677409904","https://openalex.org/W1812089471","https://openalex.org/W1979325497","https://openalex.org/W2001832505","https://openalex.org/W2005579877","https://openalex.org/W2017224880","https://openalex.org/W2021881528","https://openalex.org/W2056905427","https://openalex.org/W2061809273","https://openalex.org/W2102942431","https://openalex.org/W2116224704","https://openalex.org/W2129932701","https://openalex.org/W2145060454","https://openalex.org/W2148374900","https://openalex.org/W2149684865","https://openalex.org/W2151007976","https://openalex.org/W2151809999","https://openalex.org/W2157426404","https://openalex.org/W2158063174","https://openalex.org/W2159837087","https://openalex.org/W2165612380","https://openalex.org/W2171686321","https://openalex.org/W2185780102","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W2375180657","https://openalex.org/W2042034567","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2274831913","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W2102887023","https://openalex.org/W3204104695"],"abstract_inverted_index":{"The":[0,21,38,75,104],"paper":[1],"presents":[2],"a":[3,8,82],"general":[4],"methodology":[5],"to":[6,27,65],"implement":[7],"flexible":[9],"Focused":[10,43],"Crawler":[11,44],"for":[12],"investigation":[13],"purposes,":[14],"monitoring,":[15],"and":[16,35,56,94,118],"Open":[17],"Source":[18],"Intelligence":[19],"(OSINT).":[20],"resulting":[22],"tool":[23],"is":[24,63,107],"specifically":[25],"aimed":[26],"fit":[28],"the":[29,41,49,61,70,79,87,91,95,100,123,126],"operational":[30],"requirements":[31],"of":[32,40,51,90,125],"law-enforcement":[33],"agencies":[34],"intelligence":[36],"analyst.":[37],"architecture":[39],"semantic":[42,116],"features":[45],"static":[46],"flexibility":[47],"in":[48,59],"definition":[50],"desired":[52],"concepts,":[53],"used":[54],"metrics,":[55],"crawling":[57,96],"strategy;":[58],"addition,":[60],"method":[62,105],"capable":[64],"learn":[66],"(and":[67],"adapt":[68],"to)":[69],"analyst's":[71],"expectations":[72],"at":[73],"runtime.":[74],"user":[76],"may":[77],"instruct":[78],"crawler":[80],"with":[81,115],"binary":[83],"feedback":[84],"(yes/no)":[85],"about":[86],"current":[88],"performance":[89],"surfing":[92],"process,":[93],"engine":[97],"progressively":[98],"refines":[99],"expected":[101],"targets":[102],"accordingly.":[103],"implementation":[106],"based":[108],"on":[109],"an":[110],"existing":[111],"text-mining":[112],"environment,":[113],"integrated":[114],"networks":[117],"ontologies.":[119],"Experimental":[120],"results":[121],"witness":[122],"effectiveness":[124],"adaptive":[127],"mechanism.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
