{"id":"https://openalex.org/W1991705112","doi":"https://doi.org/10.1145/1667780.1667805","title":"Development of a large-scale web crawler and search engine infrastructure","display_name":"Development of a large-scale web crawler and search engine infrastructure","publication_year":2009,"publication_date":"2009-12-03","ids":{"openalex":"https://openalex.org/W1991705112","doi":"https://doi.org/10.1145/1667780.1667805","mag":"1991705112"},"language":"en","primary_location":{"id":"doi:10.1145/1667780.1667805","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1667780.1667805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Universal Communication Symposium","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/A5045995453","display_name":"Susumu Akamine","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Susumu Akamine","raw_affiliation_strings":["National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan","National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103965836","display_name":"Yoshikiyo Kato","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshikiyo Kato","raw_affiliation_strings":["National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan","National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102867777","display_name":"Daisuke Kawahara","orcid":"https://orcid.org/0000-0002-3598-1027"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Kawahara","raw_affiliation_strings":["National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan","National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039159478","display_name":"Keiji Shinzato","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiji Shinzato","raw_affiliation_strings":["Kyoto University, Yoshida Honmachi, Kyoto, Japan","Kyoto University, Yoshida-Honmachi, Kyoto, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Yoshida Honmachi, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Yoshida-Honmachi, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101815181","display_name":"Kentaro Inui","orcid":"https://orcid.org/0000-0001-6510-604X"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Inui","raw_affiliation_strings":["National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan and Nara Institute of Science and Technology, Ikoma, Nara, Japan","National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan and Nara Institute of Science and Technology, Ikoma, Nara, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan and Nara Institute of Science and Technology, Ikoma, Nara, Japan","institution_ids":["https://openalex.org/I75917431","https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan and Nara Institute of Science and Technology, Ikoma, Nara, Japan#TAB#","institution_ids":["https://openalex.org/I75917431","https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028836340","display_name":"Sadao Kurohashi","orcid":"https://orcid.org/0000-0001-5398-8399"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sadao Kurohashi","raw_affiliation_strings":["National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan and Kyoto University, Yoshida Honmachi, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan and Kyoto University, Yoshida Honmachi, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026289517","display_name":"Yutaka Kidawara","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yutaka Kidawara","raw_affiliation_strings":["National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan","National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Soraku-gun, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3293,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91191209,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"131"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9745000004768372,"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/T11106","display_name":"Data Management and Algorithms","score":0.96670001745224,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/web-crawler","display_name":"Web crawler","score":0.9240898489952087},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.748366117477417},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6331872344017029},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.582960844039917},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5682171583175659},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5458571910858154},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5183142423629761},{"id":"https://openalex.org/keywords/synonym","display_name":"Synonym (taxonomy)","score":0.5159016847610474},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4776265025138855},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46213454008102417},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4503142833709717},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4327138364315033}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9240898489952087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748366117477417},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6331872344017029},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.582960844039917},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5682171583175659},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5458571910858154},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5183142423629761},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.5159016847610474},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4776265025138855},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46213454008102417},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4503142833709717},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4327138364315033},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C157369684","wikidata":"https://www.wikidata.org/wiki/Q34740","display_name":"Genus","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1667780.1667805","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1667780.1667805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Universal Communication Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W47773400","https://openalex.org/W1967825155","https://openalex.org/W2066636486","https://openalex.org/W2103545802","https://openalex.org/W2127536142","https://openalex.org/W2143913708","https://openalex.org/W2145734075","https://openalex.org/W2145990704","https://openalex.org/W2405628206","https://openalex.org/W2406361246","https://openalex.org/W2602331152","https://openalex.org/W6633549240","https://openalex.org/W6638447323"],"related_works":["https://openalex.org/W3005260231","https://openalex.org/W2904469652","https://openalex.org/W4362647146","https://openalex.org/W2383572231","https://openalex.org/W4385695127","https://openalex.org/W2389761961","https://openalex.org/W4254300012","https://openalex.org/W2113184419","https://openalex.org/W1999548128","https://openalex.org/W2102475112"],"abstract_inverted_index":{"This":[0,23],"paper":[1],"reports":[2],"the":[3,26,49,62,83,89],"ongoing":[4],"development":[5],"of":[6,18,64,76,88],"a":[7,56,95],"large-scale":[8,96],"Web":[9,35],"crawler":[10],"and":[11,20,52,69,80],"search":[12],"engine":[13],"infrastructure":[14,24],"at":[15],"National":[16],"Institute":[17],"Information":[19],"Communications":[21],"Technology.":[22],"has":[25],"following":[27],"characteristics:":[28],"(1)":[29],"It":[30,42],"collects":[31],"one":[32],"billion":[33],"Japanese":[34],"pages":[36,46,51,77],"while":[37],"keeping":[38],"them":[39,54],"up-to-date.":[40],"(2)":[41],"selects":[43],"100":[44],"million":[45],"from":[47],"among":[48],"collected":[50],"converts":[53],"into":[55],"standard":[57],"data":[58,101],"format":[59],"to":[60,82],"store":[61],"results":[63],"morphological":[65],"analysis,":[66],"dependency":[67],"parsing,":[68],"synonym":[70],"augmentation.":[71],"(3)":[72],"The":[73,86],"selected":[74],"set":[75],"is":[78,91],"searchable":[79],"accessible":[81],"users.":[84],"(4)":[85],"scalability":[87],"system":[90],"achieved":[92],"by":[93],"using":[94],"cluster":[97],"machine":[98],"for":[99],"distributed":[100],"processing.":[102]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
