{"id":"https://openalex.org/W2729595233","doi":"https://doi.org/10.1186/s13635-017-0064-5","title":"Hybrid focused crawling on the Surface and the Dark Web","display_name":"Hybrid focused crawling on the Surface and the Dark Web","publication_year":2017,"publication_date":"2017-07-04","ids":{"openalex":"https://openalex.org/W2729595233","doi":"https://doi.org/10.1186/s13635-017-0064-5","mag":"2729595233"},"language":"en","primary_location":{"id":"doi:10.1186/s13635-017-0064-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13635-017-0064-5","pdf_url":"https://jis-eurasipjournals.springeropen.com/track/pdf/10.1186/s13635-017-0064-5","source":{"id":"https://openalex.org/S4210195102","display_name":"EURASIP Journal on Information Security","issn_l":"2510-523X","issn":["2510-523X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Information Security","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jis-eurasipjournals.springeropen.com/track/pdf/10.1186/s13635-017-0064-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052123762","display_name":"Christos Iliou","orcid":"https://orcid.org/0000-0002-9643-5900"},"institutions":[{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]},{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Christos Iliou","raw_affiliation_strings":["Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027935561","display_name":"George Kalpakis","orcid":"https://orcid.org/0000-0002-0862-0074"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George Kalpakis","raw_affiliation_strings":["Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045426580","display_name":"Theodora Tsikrika","orcid":"https://orcid.org/0000-0003-4148-9028"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Theodora Tsikrika","raw_affiliation_strings":["Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065313479","display_name":"Stefanos Vrochidis","orcid":"https://orcid.org/0000-0002-2505-9178"},"institutions":[{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]},{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Stefanos Vrochidis","raw_affiliation_strings":["Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084122016","display_name":"Ioannis Kompatsiaris","orcid":"https://orcid.org/0000-0001-6447-9020"},"institutions":[{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]},{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ioannis Kompatsiaris","raw_affiliation_strings":["Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052123762"],"corresponding_institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"],"apc_list":{"value":660,"currency":"GBP","value_usd":809},"apc_paid":{"value":660,"currency":"GBP","value_usd":809},"fwci":2.0204,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.8983225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2017","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9959999918937683,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9847999811172485,"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/web-crawler","display_name":"Web crawler","score":0.8829894661903381},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8345532417297363},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.8083492517471313},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7209486365318298},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.6752819418907166},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6453331708908081},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.544679582118988},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.5104483366012573},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45653682947158813},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.4288301169872284},{"id":"https://openalex.org/keywords/web-resource","display_name":"Web resource","score":0.4107622802257538},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.33685940504074097},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.24680131673812866}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8829894661903381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345532417297363},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.8083492517471313},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7209486365318298},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.6752819418907166},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6453331708908081},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.544679582118988},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.5104483366012573},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45653682947158813},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.4288301169872284},{"id":"https://openalex.org/C65603577","wikidata":"https://www.wikidata.org/wiki/Q3427877","display_name":"Web resource","level":2,"score":0.4107622802257538},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.33685940504074097},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.24680131673812866},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13635-017-0064-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13635-017-0064-5","pdf_url":"https://jis-eurasipjournals.springeropen.com/track/pdf/10.1186/s13635-017-0064-5","source":{"id":"https://openalex.org/S4210195102","display_name":"EURASIP Journal on Information Security","issn_l":"2510-523X","issn":["2510-523X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Information Security","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b9e9be0ac972459a99d8a67cbda7d5b2","is_oa":true,"landing_page_url":"https://doaj.org/article/b9e9be0ac972459a99d8a67cbda7d5b2","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Information Security, Vol 2017, Iss 1, Pp 1-13 (2017)","raw_type":"article"},{"id":"pmh:oai:zenodo.org:823206","is_oa":true,"landing_page_url":"https://zenodo.org/record/823206","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Information Security 2017","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/s13635-017-0064-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13635-017-0064-5","pdf_url":"https://jis-eurasipjournals.springeropen.com/track/pdf/10.1186/s13635-017-0064-5","source":{"id":"https://openalex.org/S4210195102","display_name":"EURASIP Journal on Information Security","issn_l":"2510-523X","issn":["2510-523X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Information Security","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G3130361054","display_name":"Retrieval and Analysis of Heterogeneous Online Content for Terrorist Activity Recognition","funder_award_id":"700024","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2729595233.pdf","grobid_xml":"https://content.openalex.org/works/W2729595233.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1897054737","https://openalex.org/W1938369530","https://openalex.org/W2001832505","https://openalex.org/W2017224880","https://openalex.org/W2045998703","https://openalex.org/W2061809273","https://openalex.org/W2080429359","https://openalex.org/W2101287943","https://openalex.org/W2102942431","https://openalex.org/W2126923252","https://openalex.org/W2175021080","https://openalex.org/W2487244534","https://openalex.org/W2567249196","https://openalex.org/W2911388033","https://openalex.org/W4236259340","https://openalex.org/W4256224324"],"related_works":["https://openalex.org/W2067523177","https://openalex.org/W2111427713","https://openalex.org/W2102942431","https://openalex.org/W2352357488","https://openalex.org/W3196389048","https://openalex.org/W2037264374","https://openalex.org/W1578408543","https://openalex.org/W2371725684","https://openalex.org/W3184910030","https://openalex.org/W2030625253"],"abstract_inverted_index":{"Focused":[0],"crawlers":[1],"enable":[2],"the":[3,17,23,32,54,57,69,77,103,108,111,116,135,155,170,173,179,182],"automatic":[4],"discovery":[5,156],"of":[6,34,110,118,139,157,172],"Web":[7,18,71,79,145,158],"resources":[8,46,159],"about":[9],"a":[10,39,86,119,129,140,143],"given":[11,49],"topic":[12,33,50],"by":[13,27,89],"automatically":[14,90],"navigating":[15],"through":[16,68],"link":[19],"structure":[20],"and":[21,72,83,95,107,142,181],"selecting":[22],"hyperlinks":[24],"to":[25,31,65],"follow":[26],"estimating":[28],"their":[29],"relevance":[30],"interest.":[35],"This":[36,148],"work":[37],"proposes":[38],"generic":[40],"focused":[41,150,175],"crawling":[42,93],"framework":[43],"for":[44,154,162,178],"discovering":[45],"on":[47,53,102,134],"any":[48],"that":[51],"reside":[52],"Surface":[55,70,180],"or":[56],"Dark":[58,78,183],"Web.":[59,184],"The":[60,166],"proposed":[61,132,174],"crawler":[62,151,176],"is":[63,152],"able":[64],"seamlessly":[66],"navigate":[67],"several":[73],"darknets":[74],"present":[75,114],"in":[76,115],"(i.e.,":[80],"Tor,":[81],"I2P,":[82],"Freenet)":[84],"during":[85],"single":[87],"crawl":[88],"adapting":[91],"its":[92,96],"behavior":[94],"classifier-guided":[97],"hyperlink":[98,124],"selection":[99,125],"strategy":[100,131],"based":[101,133],"destination":[104],"network":[105],"type":[106],"strength":[109],"local":[112],"evidence":[113],"vicinity":[117],"hyperlink.":[120],"It":[121],"investigates":[122],"11":[123],"methods,":[126],"among":[127],"which":[128],"novel":[130],"dynamic":[136],"linear":[137],"combination":[138],"link-based":[141],"parent":[144],"page":[146],"classifier.":[147],"hybrid":[149],"demonstrated":[153],"containing":[160],"recipes":[161],"producing":[163],"homemade":[164],"explosives.":[165],"evaluation":[167],"experiments":[168],"indicate":[169],"effectiveness":[171],"both":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}
