{"id":"https://openalex.org/W2138393708","doi":"https://doi.org/10.1145/1772690.1772824","title":"Measuring the web crawler ethics","display_name":"Measuring the web crawler ethics","publication_year":2010,"publication_date":"2010-04-26","ids":{"openalex":"https://openalex.org/W2138393708","doi":"https://doi.org/10.1145/1772690.1772824","mag":"2138393708"},"language":"en","primary_location":{"id":"doi:10.1145/1772690.1772824","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772824","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","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/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102285974","display_name":"Yang Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Sun","raw_affiliation_strings":["AOL Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"AOL Research, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Isaac G. Councill","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isaac G. Councill","raw_affiliation_strings":["Google Inc, New York City, NY, USA","Google, Inc., New York City, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google Inc, New York City, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc., New York City, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001294898"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":9.2848,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.977634,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1101","last_page":"1102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9984999895095825,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9984999895095825,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9958999752998352,"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":0.9742000102996826,"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":0.9558109045028687},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.8346134424209595},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6538231372833252},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5967716574668884},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46313053369522095},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4620499014854431},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.40972766280174255},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23499298095703125},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.13495326042175293},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.11680912971496582}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9558109045028687},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.8346134424209595},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6538231372833252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5967716574668884},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46313053369522095},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4620499014854431},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.40972766280174255},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23499298095703125},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.13495326042175293},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.11680912971496582}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1772690.1772824","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772824","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1967709507","https://openalex.org/W1970614016","https://openalex.org/W2037284289","https://openalex.org/W2102475166","https://openalex.org/W2122934293","https://openalex.org/W2159185913"],"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],"crawlers":[1,61,87,113,131],"are":[2,30,108],"highly":[3],"automated":[4],"and":[5,22,47,81],"seldom":[6],"regulated":[7],"manually.":[8],"The":[9,93,138],"diversity":[10],"of":[11,85,127,134],"crawler":[12,36,52,79],"activities":[13],"often":[14],"leads":[15],"to":[16,32,50,55,58,77],"ethical":[17],"problems":[18],"such":[19],"as":[20],"spam":[21],"service":[23],"attacks.":[24],"In":[25],"this":[26],"research,":[27],"quantitative":[28],"models":[29],"proposed":[31],"measure":[33,51,82,124],"the":[34,56,63,83,90,125],"web":[35,43,60,86,105],"ethics":[37,84,126],"based":[38,88],"on":[39,42,89,136],"their":[40],"behaviors":[41,107],"servers.":[44],"We":[45,71,122],"investigate":[46],"define":[48],"rules":[49],"ethics,":[53],"referring":[54],"extent":[57],"which":[59],"respect":[62],"regulations":[64],"set":[65],"forth":[66],"in":[67,132],"robots.txt":[68,120],"configuration":[69],"files.":[70],"propose":[72],"a":[73,144,152,157],"vector":[74],"space":[75],"model":[76],"represent":[78],"behavior":[80,91],"vectors.":[92],"results":[94,139],"show":[95,140],"that":[96,141],"ethicality":[97],"scores":[98],"vary":[99],"significantly":[100],"among":[101],"crawlers.":[102],"Most":[103],"commercial":[104,112],"crawlers'":[106],"ethical.":[109],"However,":[110],"many":[111],"still":[114],"consistently":[115],"violate":[116],"or":[117],"misinterpret":[118],"certain":[119],"rules.":[121],"also":[123],"big":[128],"search":[129,149],"engine":[130],"terms":[133],"return":[135],"investment.":[137],"Google":[142],"has":[143,156],"higher":[145],"score":[146,159],"than":[147,160],"other":[148],"engines":[150],"for":[151,162],"US":[153],"website":[154],"but":[155],"lower":[158],"Baidu":[161],"Chinese":[163],"websites.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}