{"id":"https://openalex.org/W2016746605","doi":"https://doi.org/10.1145/1645953.1646283","title":"URL normalization for de-duplication of web pages","display_name":"URL normalization for de-duplication of web pages","publication_year":2009,"publication_date":"2009-11-02","ids":{"openalex":"https://openalex.org/W2016746605","doi":"https://doi.org/10.1145/1645953.1646283","mag":"2016746605"},"language":"en","primary_location":{"id":"doi:10.1145/1645953.1646283","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1646283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Information and knowledge management","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/A5103174125","display_name":"Amit Agarwal","orcid":"https://orcid.org/0000-0002-7642-1341"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Amit Agarwal","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064400393","display_name":"Hema Swetha Koppula","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hema Swetha Koppula","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069768149","display_name":"Krishna P. Leela","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Krishna P. Leela","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049093178","display_name":"Krishna Prasad Chitrapura","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Krishna Prasad Chitrapura","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100896317","display_name":"Sachin Garg","orcid":"https://orcid.org/0009-0004-6719-5866"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sachin Garg","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080488779","display_name":"P. Senthil Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pavan Kumar GM","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067589777","display_name":"Chittaranjan Haty","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chittaranjan Haty","raw_affiliation_strings":["Yahoo! Inc., Bangalore, India","Yahoo! Inc., Bangalore, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo! Inc., Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"Yahoo! Inc., Bangalore, India#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076846018","display_name":"Anirban Roy","orcid":"https://orcid.org/0009-0000-6889-0204"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anirban Roy","raw_affiliation_strings":["Yahoo! Inc., Bangalore, India","Yahoo! Inc., Bangalore, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo! Inc., Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"Yahoo! Inc., Bangalore, India#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017186997","display_name":"Amit Sasturkar","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Amit Sasturkar","raw_affiliation_strings":["Yahoo! Inc., Sunnyvale, CA, USA","Yahoo, Inc., Sunnyvale, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo! Inc., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo, Inc., Sunnyvale, CA, USA#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5103174125"],"corresponding_institution_ids":["https://openalex.org/I1325784139"],"apc_list":null,"apc_paid":null,"fwci":6.9726,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.9675065,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1987","last_page":"1990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","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/T12016","display_name":"Web Data Mining and Analysis","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/T11719","display_name":"Data Quality and Management","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.993399977684021,"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/computer-science","display_name":"Computer science","score":0.7889472246170044},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.670562744140625},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.668320894241333},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.593733012676239},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5921544432640076},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.5562451481819153},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.532752513885498},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.49738600850105286},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.4799545109272003},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47467827796936035},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46451181173324585},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42793431878089905},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4182715117931366},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.26003772020339966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7889472246170044},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.670562744140625},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.668320894241333},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.593733012676239},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5921544432640076},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.5562451481819153},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.532752513885498},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.49738600850105286},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.4799545109272003},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47467827796936035},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46451181173324585},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42793431878089905},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4182715117931366},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.26003772020339966},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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":2,"locations":[{"id":"doi:10.1145/1645953.1646283","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1646283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.8185","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.8185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cornell.edu/~hema/papers/sp0955-agarwalATS.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1587314265","https://openalex.org/W1775663022","https://openalex.org/W1854214752","https://openalex.org/W1986968077","https://openalex.org/W1990061958","https://openalex.org/W2085922539","https://openalex.org/W2112104357","https://openalex.org/W2132069633","https://openalex.org/W2139532006","https://openalex.org/W2145349611","https://openalex.org/W2149706766","https://openalex.org/W2158601853","https://openalex.org/W4241558715"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W2137810919","https://openalex.org/W4255854114","https://openalex.org/W4385695127"],"abstract_inverted_index":{"Presence":[0],"of":[1,21,31,58,66,93,106,133],"duplicate":[2],"documents":[3],"in":[4],"the":[5,17,51,60,90,104,110,131],"World":[6],"Wide":[7],"Web":[8],"adversely":[9],"affects":[10],"crawling,":[11],"indexing":[12],"and":[13,38,63],"relevance,":[14],"which":[15,108],"are":[16,122],"core":[18],"building":[19],"blocks":[20],"web":[22],"search.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"present":[28,97],"a":[29,98],"set":[30,105],"techniques":[32,121,135],"to":[33,69,76,89,102,113],"mine":[34],"rules":[35,42,72,82],"from":[36,73],"URLs":[37,74],"utilize":[39],"these":[40],"learnt":[41],"for":[43,83],"de-duplication":[44,84],"using":[45],"just":[46],"URL":[47,127],"strings":[48],"without":[49],"fetching":[50],"content":[52],"explicitly.":[53],"Our":[54],"technique":[55,101],"is":[56,85],"composed":[57],"mining":[59],"crawl":[61],"logs":[62],"utilizing":[64],"clusters":[65],"similar":[67],"pages":[68],"extract":[70],"specific":[71,94,126],"belonging":[75],"each":[77,80],"cluster.":[78],"Preserving":[79],"mined":[81],"not":[86],"efficient":[87],"due":[88],"large":[91],"number":[92],"rules.":[95],"We":[96,129],"machine":[99],"learning":[100],"generalize":[103],"rules,":[107],"reduces":[109],"resource":[111],"footprint":[112],"be":[114],"usable":[115],"at":[116],"web-scale.":[117],"The":[118],"rule":[119],"extraction":[120],"robust":[123],"against":[124],"web-site":[125],"conventions.":[128],"demonstrate":[130],"effectiveness":[132],"our":[134],"through":[136],"experimental":[137],"evaluation.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
