{"id":"https://openalex.org/W2520953810","doi":"https://doi.org/10.1093/comjnl/bxw072","title":"WIVET\u2014Benchmarking Coverage Qualities of Web Crawlers","display_name":"WIVET\u2014Benchmarking Coverage Qualities of Web Crawlers","publication_year":2016,"publication_date":"2016-09-12","ids":{"openalex":"https://openalex.org/W2520953810","doi":"https://doi.org/10.1093/comjnl/bxw072","mag":"2520953810"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxw072","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxw072","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-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/A5087110439","display_name":"Emin \u0130slam Tatl\u0131","orcid":"https://orcid.org/0000-0003-4562-8486"},"institutions":[{"id":"https://openalex.org/I3125470973","display_name":"Istanbul Medipol University","ror":"https://ror.org/037jwzz50","country_code":"TR","type":"education","lineage":["https://openalex.org/I3125470973"]},{"id":"https://openalex.org/I4210092500","display_name":"T\u00fcrk Telekom (Turkey)","ror":"https://ror.org/002famp79","country_code":"TR","type":"company","lineage":["https://openalex.org/I4210092500"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Emi\u0307n \u0130slam Tatli","raw_affiliation_strings":["Department of Electrical and Electronics Engineering, Istanbul Medipol University, Kavac\u0131k Mah. Ekinciler Cad. No. 19 34810 Beykoz-Istanbul, Turkey","T\u00fcrk Telekom R & D Technology Center, \u00dcntel Sk. No:7, 34768 \u00dcmraniye-Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, Istanbul Medipol University, Kavac\u0131k Mah. Ekinciler Cad. No. 19 34810 Beykoz-Istanbul, Turkey","institution_ids":["https://openalex.org/I3125470973"]},{"raw_affiliation_string":"T\u00fcrk Telekom R & D Technology Center, \u00dcntel Sk. No:7, 34768 \u00dcmraniye-Istanbul, Turkey","institution_ids":["https://openalex.org/I4210092500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077644636","display_name":"Bedi\u0307rhan Urgun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bedi\u0307rhan Urgun","raw_affiliation_strings":["NormShield Inc. 8201 Greensboro Drive, Suite 300 McLean, VA 22102, USA"],"affiliations":[{"raw_affiliation_string":"NormShield Inc. 8201 Greensboro Drive, Suite 300 McLean, VA 22102, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087110439"],"corresponding_institution_ids":["https://openalex.org/I3125470973","https://openalex.org/I4210092500"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":3.9808,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94380534,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":1.0,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":1.0,"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":0.9894999861717224,"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":0.9861999750137329,"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":0.9456791877746582},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8424677848815918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7832349538803101},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.6488877534866333},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4737818241119385},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.4298752546310425},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4202854335308075},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4079431891441345},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.3884021043777466},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3863771855831146},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.25504493713378906},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.15888461470603943},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12840330600738525},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.10822078585624695}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9456791877746582},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8424677848815918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832349538803101},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.6488877534866333},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4737818241119385},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.4298752546310425},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4202854335308075},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4079431891441345},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3884021043777466},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3863771855831146},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.25504493713378906},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.15888461470603943},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12840330600738525},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.10822078585624695},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/comjnl/bxw072","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxw072","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W96862218","https://openalex.org/W1489243061","https://openalex.org/W1517402704","https://openalex.org/W1601949013","https://openalex.org/W1861561811","https://openalex.org/W1879579243","https://openalex.org/W1976216148","https://openalex.org/W1979931683","https://openalex.org/W2011539648","https://openalex.org/W2028476081","https://openalex.org/W2050396717","https://openalex.org/W2085925880","https://openalex.org/W2109183627","https://openalex.org/W2110034127","https://openalex.org/W2111607551","https://openalex.org/W2119852587","https://openalex.org/W2119871945","https://openalex.org/W2124291742","https://openalex.org/W2132791332","https://openalex.org/W2135583690","https://openalex.org/W2148738951","https://openalex.org/W2152725427","https://openalex.org/W2165698272","https://openalex.org/W2171644977"],"related_works":["https://openalex.org/W1501777393","https://openalex.org/W2042034567","https://openalex.org/W2548443989","https://openalex.org/W2375180657","https://openalex.org/W4385695127","https://openalex.org/W2963706618","https://openalex.org/W2113184419","https://openalex.org/W2389761961","https://openalex.org/W1999548128","https://openalex.org/W4254300012"],"abstract_inverted_index":{"Web":[0],"application":[1,50],"vulnerability":[2],"scanners":[3],"(WAVS)":[4],"include":[5],"crawler":[6,60,88,132],"components":[7,133],"to":[8,19,41,68],"extract":[9],"all":[10,164],"accessible":[11],"links":[12,71,148,170],"of":[13,33,75,86,97,115,134,145,175],"tested":[14,48],"web":[15,49],"pages":[16],"in":[17,46,94,185],"order":[18],"identify":[20],"attack":[21],"entry":[22],"points":[23],"and":[24,39,111,168,181],"parameters.":[25],"After":[26],"extracting":[27],"links,":[28],"they":[29],"perform":[30],"different":[31],"types":[32],"attacks":[34],"over":[35],"each":[36],"extracted":[37],"link":[38],"try":[40],"find":[42],"out":[43],"existing":[44,70],"vulnerabilities":[45,77],"the":[47,83,95],"for":[51,109,130],"reporting.":[52],"A":[53],"WAVS":[54,99,116,138,178,182],"tool":[55,129],"that":[56,149],"has":[57],"a":[58,90,98,106,127],"low-quality":[59],"component":[61],"would":[62,72],"generate":[63],"false-negative":[64],"results,":[65],"since":[66],"failing":[67],"discover":[69],"inhibit":[73],"detection":[74],"possible":[76],"exposed":[78],"through":[79],"these":[80],"links.":[81],"Therefore,":[82],"coverage":[84,113],"quality":[85],"its":[87],"plays":[89],"very":[91],"important":[92],"role":[93],"success":[96],"tool.":[100],"In":[101],"this":[102],"paper,":[103],"we":[104],"propose":[105],"novel":[107],"method":[108],"analyzing":[110,131],"comparing":[112],"qualities":[114],"crawlers.":[117],"We":[118,160],"developed":[119],"WIVET":[120,136,165,176],"(Web":[121],"Input":[122],"Vector":[123],"Extractor":[124],"Teaser)":[125],"as":[126],"benchmarking":[128,183],"WAVS.":[135],"evaluates":[137],"crawlers":[139],"based":[140],"on":[141],"their":[142],"extraction":[143],"capability":[144],"56":[146],"target":[147,169],"are":[150],"generated":[151],"statically":[152],"or":[153],"dynamically":[154],"by":[155],"WIVET's":[156,162],"21":[157],"test":[158,166],"cases.":[159],"explain":[161],"architecture,":[163],"cases":[167],"with":[171],"code":[172],"examples,":[173],"integration":[174],"into":[177],"development":[179],"environments":[180],"results":[184],"detail.":[186]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
