{"id":"https://openalex.org/W2109028086","doi":"https://doi.org/10.1145/1135777.1135822","title":"Geographically focused collaborative crawling","display_name":"Geographically focused collaborative crawling","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2109028086","doi":"https://doi.org/10.1145/1135777.1135822","mag":"2109028086"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135822","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/A5084505804","display_name":"Weizheng Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167196","display_name":"Minnow Environmental (Canada)","ror":"https://ror.org/05petyd50","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210167196"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Weizheng Gao","raw_affiliation_strings":["Genieknows.com, Halifax, NS, Canada","Genieknows.com, Halifax, NS, Canada#TAB#"],"affiliations":[{"raw_affiliation_string":"Genieknows.com, Halifax, NS, Canada","institution_ids":[]},{"raw_affiliation_string":"Genieknows.com, Halifax, NS, Canada#TAB#","institution_ids":["https://openalex.org/I4210167196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101945970","display_name":"Hyun Chul Lee","orcid":"https://orcid.org/0000-0003-3136-0810"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hyun Chul Lee","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada","University of Toronto, Toronto, On, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto, Toronto, On, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018055848","display_name":"Yingbo Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167196","display_name":"Minnow Environmental (Canada)","ror":"https://ror.org/05petyd50","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210167196"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yingbo Miao","raw_affiliation_strings":["Genieknows.com, Halifax, NS, Canada","Genieknows.com, Halifax, NS, Canada#TAB#"],"affiliations":[{"raw_affiliation_string":"Genieknows.com, Halifax, NS, Canada","institution_ids":[]},{"raw_affiliation_string":"Genieknows.com, Halifax, NS, Canada#TAB#","institution_ids":["https://openalex.org/I4210167196"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084505804"],"corresponding_institution_ids":["https://openalex.org/I4210167196"],"apc_list":null,"apc_paid":null,"fwci":12.3124,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.9810248,"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":"287","last_page":"296"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9940000176429749,"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"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9865999817848206,"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/crawling","display_name":"Crawling","score":0.9637035131454468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7763264775276184},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6791467070579529},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5828850269317627},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45045924186706543},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.42755404114723206},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.41916680335998535},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06765556335449219}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9637035131454468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763264775276184},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6791467070579529},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5828850269317627},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45045924186706543},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.42755404114723206},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.41916680335998535},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06765556335449219},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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":1,"locations":[{"id":"doi:10.1145/1135777.1135822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135822","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":23,"referenced_works":["https://openalex.org/W173995639","https://openalex.org/W1489992655","https://openalex.org/W1496059925","https://openalex.org/W1521219253","https://openalex.org/W1604630858","https://openalex.org/W1608864735","https://openalex.org/W1613836731","https://openalex.org/W1979987551","https://openalex.org/W1985182453","https://openalex.org/W1989813732","https://openalex.org/W2005579877","https://openalex.org/W2014134732","https://openalex.org/W2017726337","https://openalex.org/W2018928332","https://openalex.org/W2029341294","https://openalex.org/W2059984218","https://openalex.org/W2119159732","https://openalex.org/W2124673015","https://openalex.org/W2127387319","https://openalex.org/W2138621811","https://openalex.org/W2162502927","https://openalex.org/W2295141584","https://openalex.org/W3141829038"],"related_works":["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/W2089702591","https://openalex.org/W4255854114","https://openalex.org/W4385695127"],"abstract_inverted_index":{"A":[0],"collaborative":[1,32,39,117],"crawler":[2],"is":[3,14,49],"a":[4,17],"group":[5],"of":[6,20,27,64,67,72,86,106,139,145],"crawling":[7,12,33,40,88,95,98,108,122],"nodes,":[8],"in":[9,119],"which":[10,120],"each":[11],"node":[13],"responsible":[15],"for":[16,42,155],"specific":[18],"portion":[19],"the":[21,25,43,84,99,112,121,128,151,156],"web.":[22],"We":[23,35],"study":[24,93],"problem":[26],"collecting":[28],"geographi-cally-aware":[29],"pages":[30,53],"using":[31],"strategies.":[34,89],"first":[36],"propose":[37,78],"several":[38],"strategies":[41,96,109],"geographically":[44,157],"focused":[45,158],"crawling,":[46,118],"whose":[47],"goal":[48],"to":[50,82,127,149],"collect":[51],"web":[52,101],"about":[54],"specified":[55],"geographic":[56],"locations,":[57],"by":[58,97],"considering":[59],"features":[60,135],"like":[61,136],"URL":[62,137],"address":[63,138],"page,":[65,68],"content":[66],"extended":[69,142],"anchor":[70,143],"text":[71,144],"link,":[73],"and":[74,141],"others.":[75],"Later,":[76],"we":[77,91],"various":[79],"evaluation":[80],"criteria":[81],"qualify":[83],"performance":[85,154],"such":[87],"Finally,":[90],"experimentally":[92],"our":[94,107],"real":[100],"data":[102],"showing":[103],"that":[104],"some":[105],"greatly":[110],"outperform":[111],"simple":[113],"URL-hash":[114],"based":[115],"partition":[116],"assignments":[123],"are":[124,147],"determined":[125],"according":[126],"hash-value":[129],"computation":[130],"over":[131],"URLs.":[132],"More":[133],"precisely,":[134],"page":[140],"link":[146],"shown":[148],"yield":[150],"best":[152],"overall":[153],"crawling.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
