{"id":"https://openalex.org/W2796214649","doi":"https://doi.org/10.1145/3201064.3201091","title":"Automated Discovery of Internet Censorship by Web Crawling","display_name":"Automated Discovery of Internet Censorship by Web Crawling","publication_year":2018,"publication_date":"2018-05-15","ids":{"openalex":"https://openalex.org/W2796214649","doi":"https://doi.org/10.1145/3201064.3201091","mag":"2796214649"},"language":"en","primary_location":{"id":"doi:10.1145/3201064.3201091","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3201064.3201091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM Conference on Web Science","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.03056","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Alexander Darer","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Alexander Darer","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Oliver Farnan","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Farnan","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":null,"display_name":"Joss Wright","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joss Wright","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":0.3384,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67315761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9987000226974487,"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/T11478","display_name":"Caching and Content Delivery","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/censorship","display_name":"Censorship","score":0.88919997215271},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8130999803543091},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6931999921798706},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.6905999779701233},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6220999956130981},{"id":"https://openalex.org/keywords/public-domain","display_name":"Public domain","score":0.5227000117301941},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5059999823570251},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.42010000348091125}],"concepts":[{"id":"https://openalex.org/C52930066","wikidata":"https://www.wikidata.org/wiki/Q543","display_name":"Censorship","level":2,"score":0.88919997215271},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8130999803543091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275999784469604},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6931999921798706},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.6905999779701233},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6220999956130981},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6191999912261963},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.38929998874664307},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34150001406669617},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.33399999141693115},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C2775833480","wikidata":"https://www.wikidata.org/wiki/Q26084","display_name":"Freedom of information","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C1173588","wikidata":"https://www.wikidata.org/wiki/Q6554294","display_name":"Link analysis","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.25870001316070557}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3201064.3201091","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3201064.3201091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM Conference on Web Science","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.03056","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.03056","pdf_url":"https://arxiv.org/pdf/1804.03056","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1804.03056","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.03056","pdf_url":"https://arxiv.org/pdf/1804.03056","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1974616087","https://openalex.org/W2012152947","https://openalex.org/W2028060714","https://openalex.org/W2087027277","https://openalex.org/W2126053700","https://openalex.org/W2134747589","https://openalex.org/W2153156723","https://openalex.org/W2168006138","https://openalex.org/W2201189541","https://openalex.org/W2292723020","https://openalex.org/W2535378852","https://openalex.org/W2561535538","https://openalex.org/W2618275734","https://openalex.org/W2733812526","https://openalex.org/W2964219251","https://openalex.org/W3124321814"],"related_works":[],"abstract_inverted_index":{"Censorship":[0],"of":[1,18,67,80,136,163,174,185,197,208],"the":[2,7,12,68,78,134,137,160,164,178,194,204],"Internet":[3],"is":[4,36,101,130],"widespread":[5],"around":[6],"world.":[8],"As":[9],"access":[10,34],"to":[11,35,59,115,142],"web":[13,112,210],"becomes":[14,21],"increasingly":[15],"ubiquitous,":[16],"filtering":[17,81],"this":[19],"resource":[20],"more":[22],"pervasive.":[23],"Transparency":[24],"about":[25],"specific":[26],"content":[27,146,199],"and":[28,55,70,104,120,166,202],"information":[29],"that":[30,155],"citizens":[31],"are":[32],"denied":[33],"atypical.":[37],"To":[38],"counter":[39],"this,":[40],"numerous":[41],"techniques":[42,114],"for":[43,65,91,125,144],"maintaining":[44],"URL":[45],"filter":[46,170],"lists":[47,171,183],"have":[48,167],"been":[49],"proposed":[50],"by":[51,83,139],"various":[52],"individuals,":[53],"organisations":[54],"researchers.":[56],"These":[57],"aim":[58],"improve":[60],"empirical":[61],"data":[62],"on":[63],"censorship":[64,72,150],"benefit":[66],"public":[69,182],"wider":[71],"research":[73],"community,":[74],"while":[75],"also":[76],"increasing":[77],"transparency":[79],"activity":[82],"oppressive":[84],"regimes.":[85,151],"We":[86,132],"present":[87],"a":[88,122,128,191],"new":[89],"approach":[90,138],"discovering":[92],"filtered":[93,118,145],"domains":[94,201],"in":[95,147],"different":[96,149],"target":[97],"countries.":[98],"This":[99],"method":[100,124],"fully":[102],"automated":[103],"requires":[105],"no":[106],"human":[107],"interaction.":[108],"The":[109],"system":[110],"uses":[111],"crawling":[113],"traverse":[116],"between":[117,200],"sites":[119],"implements":[121],"robust":[123],"determining":[126],"if":[127],"domain":[129,169],"filtered.":[131],"demonstrate":[133],"effectiveness":[135],"running":[140],"experiments":[141],"search":[143],"four":[148],"Our":[152],"results":[153],"show":[154],"we":[156,189],"perform":[157],"better":[158],"than":[159,177],"current":[161],"state":[162],"art":[165],"built":[168],"an":[172],"order":[173],"magnitude":[175],"larger":[176],"most":[179],"widely":[180],"available":[181],"as":[184],"April":[186],"2018.":[187],"Further,":[188],"build":[190],"dataset":[192],"mapping":[193],"interlinking":[195],"nature":[196,207],"blocked":[198],"exhibit":[203],"tightly":[205],"networked":[206],"censored":[209],"resources.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2018-04-13T00:00:00"}
