{"id":"https://openalex.org/W1989813732","doi":"https://doi.org/10.1145/1096985.1096999","title":"Geographical partition for distributed web crawling","display_name":"Geographical partition for distributed web crawling","publication_year":2005,"publication_date":"2005-11-04","ids":{"openalex":"https://openalex.org/W1989813732","doi":"https://doi.org/10.1145/1096985.1096999","mag":"1989813732"},"language":"en","primary_location":{"id":"doi:10.1145/1096985.1096999","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1096985.1096999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 workshop on Geographic information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10198/526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066596025","display_name":"Jos\u00e9 Exposto","orcid":"https://orcid.org/0000-0003-3857-6083"},"institutions":[{"id":"https://openalex.org/I4210092303","display_name":"Polytechnic Institute of Bragan\u00e7a","ror":"https://ror.org/00prsav78","country_code":"PT","type":"education","lineage":["https://openalex.org/I4210092303"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Exposto","raw_affiliation_strings":["Instituto Polit\u00e9cnico de Bragan\u00e7a, Bragan\u00e7a, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Polit\u00e9cnico de Bragan\u00e7a, Bragan\u00e7a, Portugal","institution_ids":["https://openalex.org/I4210092303"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028286071","display_name":"Joaquim Macedo","orcid":"https://orcid.org/0000-0002-5892-1289"},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Joaquim Macedo","raw_affiliation_strings":["Universidade do Minho, Braga - Portugal","[Universidade do Minho, Braga, Portugal]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade do Minho, Braga - Portugal","institution_ids":["https://openalex.org/I99682543"]},{"raw_affiliation_string":"[Universidade do Minho, Braga, Portugal]","institution_ids":["https://openalex.org/I99682543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077589526","display_name":"Ant\u00f3nio Manuel Silva Pina","orcid":"https://orcid.org/0000-0001-6548-6396"},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Ant\u00f3nio Pina","raw_affiliation_strings":["Universidade do Minho, Braga - Portugal","[Universidade do Minho, Braga, Portugal]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade do Minho, Braga - Portugal","institution_ids":["https://openalex.org/I99682543"]},{"raw_affiliation_string":"[Universidade do Minho, Braga, Portugal]","institution_ids":["https://openalex.org/I99682543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051048442","display_name":"Albano Alves","orcid":"https://orcid.org/0000-0001-9796-6810"},"institutions":[{"id":"https://openalex.org/I4210092303","display_name":"Polytechnic Institute of Bragan\u00e7a","ror":"https://ror.org/00prsav78","country_code":"PT","type":"education","lineage":["https://openalex.org/I4210092303"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Albano Alves","raw_affiliation_strings":["Instituto Polit\u00e9cnico de Bragan\u00e7a, Bragan\u00e7a, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Polit\u00e9cnico de Bragan\u00e7a, Bragan\u00e7a, Portugal","institution_ids":["https://openalex.org/I4210092303"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008882289","display_name":"Jos\u00e9 Rufino","orcid":"https://orcid.org/0000-0002-1344-8264"},"institutions":[{"id":"https://openalex.org/I4210092303","display_name":"Polytechnic Institute of Bragan\u00e7a","ror":"https://ror.org/00prsav78","country_code":"PT","type":"education","lineage":["https://openalex.org/I4210092303"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Rufino","raw_affiliation_strings":["Instituto Polit\u00e9cnico de Bragan\u00e7a, Bragan\u00e7a, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Polit\u00e9cnico de Bragan\u00e7a, Bragan\u00e7a, Portugal","institution_ids":["https://openalex.org/I4210092303"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.4858,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.97052529,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.80751633644104},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.759351372718811},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6941759586334229},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6458033919334412},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.6114181876182556},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5995499491691589},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.5500317215919495},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.5263035297393799},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5232571363449097},{"id":"https://openalex.org/keywords/download","display_name":"Download","score":0.4661105275154114},{"id":"https://openalex.org/keywords/backlink","display_name":"Backlink","score":0.4466731548309326},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.43880563974380493},{"id":"https://openalex.org/keywords/stateless-protocol","display_name":"Stateless protocol","score":0.4330800175666809},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.41383129358291626},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32417961955070496},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.2808372676372528},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.1922932267189026},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16395840048789978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80751633644104},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.759351372718811},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6941759586334229},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6458033919334412},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.6114181876182556},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5995499491691589},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.5500317215919495},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.5263035297393799},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5232571363449097},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.4661105275154114},{"id":"https://openalex.org/C71325787","wikidata":"https://www.wikidata.org/wiki/Q373952","display_name":"Backlink","level":5,"score":0.4466731548309326},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.43880563974380493},{"id":"https://openalex.org/C103613024","wikidata":"https://www.wikidata.org/wiki/Q230924","display_name":"Stateless protocol","level":3,"score":0.4330800175666809},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.41383129358291626},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32417961955070496},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.2808372676372528},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.1922932267189026},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16395840048789978},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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":4,"locations":[{"id":"doi:10.1145/1096985.1096999","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1096985.1096999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 workshop on Geographic information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:bibliotecadigital.ipb.pt:10198/526","is_oa":true,"landing_page_url":"http://hdl.handle.net/10198/526","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},{"id":"pmh:oai:repositorium.sdum.uminho.pt:1822/6321","is_oa":true,"landing_page_url":"http://hdl.handle.net/1822/6321","pdf_url":null,"source":{"id":"https://openalex.org/S4306401240","display_name":"Reposit\u00f3riUM (Universidade do Minho)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99682543","host_organization_name":"University of Minho","host_organization_lineage":["https://openalex.org/I99682543"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"},{"id":"pmh:oai:repositorium.uminho.pt:1822/6321","is_oa":true,"landing_page_url":"https://hdl.handle.net/1822/6321","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:bibliotecadigital.ipb.pt:10198/526","is_oa":true,"landing_page_url":"http://hdl.handle.net/10198/526","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W60551819","https://openalex.org/W1489992655","https://openalex.org/W1521219253","https://openalex.org/W1995855646","https://openalex.org/W2005579877","https://openalex.org/W2008620264","https://openalex.org/W2059984218","https://openalex.org/W2070232376","https://openalex.org/W2140199883","https://openalex.org/W2295141584","https://openalex.org/W2714497087","https://openalex.org/W3104001151","https://openalex.org/W6602496796","https://openalex.org/W6631106333","https://openalex.org/W6649345576"],"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/W2964752624","https://openalex.org/W3162066371","https://openalex.org/W2113184419"],"abstract_inverted_index":{"This":[0],"paper":[1],"evaluates":[2],"scalable":[3],"distributed":[4,24,45],"crawling":[5],"by":[6],"means":[7],"of":[8,12,22,50,65,84,96,115,138],"the":[9,13,20,30,48,62,81,85,94,105,110,116,122,135],"geographical":[10,39,59,89,103],"partition":[11,70],"Web.":[14],"The":[15,41],"approach":[16,149],"is":[17,54,107],"based":[18,55],"on":[19,56],"existence":[21],"multiple":[23],"crawlers":[25],"each":[26],"one":[27,34],"responsible":[28],"for":[29],"pages":[31,51,139],"belonging":[32],"to":[33,52,68,109,127,146,150],"or":[35],"more":[36],"previously":[37],"identified":[38],"zones.":[40],"work":[42],"considers":[43],"a":[44,66,69,73,78,97,101],"crawler":[46],"where":[47],"assignment":[49,64],"visit":[53],"page":[57,67,79,98,106,130],"content":[58],"scope.":[60],"For":[61],"initial":[63],"we":[71],"use":[72],"simple":[74],"heuristic":[75],"that":[76],"marks":[77],"within":[80],"same":[82],"scope":[83],"hosting":[86],"web":[87,112],"server":[88],"location.":[90],"During":[91],"download,":[92],"if":[93],"analyze":[95],"contents":[99],"recommends":[100],"different":[102],"scope,":[104],"forwarded":[108],"well-located":[111],"server.A":[113],"sample":[114],"Portuguese":[117],"Web":[118],"pages,":[119],"extracted":[120],"during":[121],"year":[123],"2005,":[124],"was":[125],"used":[126],"evaluate:":[128],"a)":[129],"download":[131],"communication":[132],"times":[133],"and":[134],"b)":[136],"overhead":[137],"exchange":[140],"among":[141],"servers.":[142],"Evaluation":[143],"results":[144],"permit":[145],"compare":[147],"our":[148],"conventional":[151],"hash":[152],"partitioning":[153],"strategies.":[154]},"counts_by_year":[{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6}],"updated_date":"2026-07-04T07:58:01.006859","created_date":"2025-10-10T00:00:00"}
