{"id":"https://openalex.org/W2112104357","doi":"https://doi.org/10.1145/1135777.1135992","title":"Do not crawl in the DUST","display_name":"Do not crawl in the DUST","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2112104357","doi":"https://doi.org/10.1145/1135777.1135992","mag":"2112104357"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135992","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th 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/A5052102699","display_name":"Uri Schonfeld","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Uri Schonfeld","raw_affiliation_strings":["Technion, Haifa, Israel","Technion , Haifa , Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Technion , Haifa , Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054834255","display_name":"Ziv Bar-Yossef","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ziv Bar-Yossef","raw_affiliation_strings":["Technion, Haifa, Israel","Technion , Haifa , Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Technion , Haifa , Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059238786","display_name":"Idit Keidar","orcid":"https://orcid.org/0000-0002-6417-1250"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Idit Keidar","raw_affiliation_strings":["Technion, Haifa, Israel","Technion , Haifa , Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Technion , Haifa , Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052102699"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":19.7002,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.99105321,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1015","last_page":"1016"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9966999888420105,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8178074955940247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8037556409835815},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7506538033485413},{"id":"https://openalex.org/keywords/pagerank","display_name":"PageRank","score":0.7318932414054871},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6455562114715576},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5825706124305725},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5655502080917358},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5282703638076782},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5252185463905334},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.5084813833236694},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5078797936439514},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.4864037334918976},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.47232168912887573},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4146057963371277},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4105462431907654},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35509586334228516},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34556883573532104},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2118750810623169},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.19497093558311462},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.1333279311656952},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11296507716178894}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8178074955940247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037556409835815},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7506538033485413},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.7318932414054871},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6455562114715576},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5825706124305725},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5655502080917358},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5282703638076782},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5252185463905334},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5084813833236694},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5078797936439514},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.4864037334918976},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.47232168912887573},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4146057963371277},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4105462431907654},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35509586334228516},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34556883573532104},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2118750810623169},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.19497093558311462},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.1333279311656952},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11296507716178894},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1135777.1135992","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th 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":34,"referenced_works":["https://openalex.org/W1484413656","https://openalex.org/W1484743740","https://openalex.org/W1506285740","https://openalex.org/W1511974523","https://openalex.org/W1536700701","https://openalex.org/W1543335880","https://openalex.org/W1546842576","https://openalex.org/W1557168499","https://openalex.org/W1567365482","https://openalex.org/W1597291463","https://openalex.org/W1965657003","https://openalex.org/W1983578042","https://openalex.org/W1990061958","https://openalex.org/W1991548210","https://openalex.org/W1997438973","https://openalex.org/W2005112587","https://openalex.org/W2007842132","https://openalex.org/W2011039300","https://openalex.org/W2046166587","https://openalex.org/W2047221353","https://openalex.org/W2066636486","https://openalex.org/W2100935296","https://openalex.org/W2136774890","https://openalex.org/W2141359307","https://openalex.org/W2152505903","https://openalex.org/W2152565070","https://openalex.org/W2161532103","https://openalex.org/W2164634022","https://openalex.org/W2166776180","https://openalex.org/W2169189540","https://openalex.org/W2171500543","https://openalex.org/W2187227553","https://openalex.org/W2401330804","https://openalex.org/W3145042860"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2097808084","https://openalex.org/W2095543197","https://openalex.org/W2371838993"],"abstract_inverted_index":{"We":[0,45],"consider":[1],"the":[2,37,112,123],"problem":[3],"of":[4,114,125],"dust:":[5],"Different":[6],"URLs":[7,13,29],"with":[8],"Similar":[9],"Text.":[10],"Such":[11],"duplicate":[12],"are":[14,67],"prevalent":[15],"in":[16],"web":[17,20,85,101],"sites,":[18],"as":[19,119,121,129],"server":[21,86],"software":[22],"often":[23],"uses":[24],"aliases":[25],"and":[26,34],"redirections,":[27],"translates":[28],"to":[30,64,69,76,110],"some":[31],"canonical":[32],"form,":[33],"dynamically":[35],"generates":[36],"same":[38],"page":[39,90],"from":[40,80,107],"various":[41],"different":[42],"URL":[43,63],"requests.":[44],"present":[46],"a":[47,61],"novel":[48],"algorithm,":[49],"DustBuster,":[50],"for":[51,56,59],"uncovering":[52],"dust;":[53],"that":[54,66],"is,":[55],"discovering":[57],"rules":[58,94],"transforming":[60],"given":[62],"others":[65],"likely":[68],"have":[70],"similar":[71],"content.":[72],"DustBuster":[73],"is":[74],"able":[75],"detect":[77],"dust":[78],"effectively":[79],"previous":[81],"crawl":[82],"logs":[83],"or":[84],"logs,":[87],"without":[88],"examining":[89],"contents.":[91],"Verifying":[92],"these":[93],"via":[95],"sampling":[96],"requires":[97],"fetching":[98],"few":[99],"actual":[100],"pages.":[102],"Search":[103],"engines":[104],"can":[105],"benefit":[106],"this":[108],"information":[109],"increase":[111],"effectiveness":[113],"crawling,":[115],"reduce":[116],"indexing":[117],"overhead":[118],"well":[120],"improve":[122],"quality":[124],"popularity":[126],"statistics":[127],"such":[128],"PageRank.":[130]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
