{"id":"https://openalex.org/W2243366197","doi":"https://doi.org/10.1145/2567948.2577271","title":"Scalability and efficiency challenges in large-scale web search engines","display_name":"Scalability and efficiency challenges in large-scale web search engines","publication_year":2014,"publication_date":"2014-04-07","ids":{"openalex":"https://openalex.org/W2243366197","doi":"https://doi.org/10.1145/2567948.2577271","mag":"2243366197"},"language":"en","primary_location":{"id":"doi:10.1145/2567948.2577271","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2567948.2577271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd 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/A5076204770","display_name":"Ricardo Baeza\u2010Yates","orcid":"https://orcid.org/0000-0003-3208-9778"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Ricardo Baeza-Yates","raw_affiliation_strings":["Yahoo Labs, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo Labs, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015615642","display_name":"B. Barla Cambazo\u011flu","orcid":"https://orcid.org/0000-0003-2192-3819"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"B. Barla Cambazoglu","raw_affiliation_strings":["Yahoo Labs, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Yahoo Labs, Barcelona, Spain","institution_ids":["https://openalex.org/I2800095910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076204770"],"corresponding_institution_ids":["https://openalex.org/I2800095910"],"apc_list":null,"apc_paid":null,"fwci":4.7334,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.95187655,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"185","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9921000003814697,"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":0.8292413949966431},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7843427658081055},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7757136821746826},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6702110767364502},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5803855061531067},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4840511679649353},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.47373974323272705},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4492442011833191},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.4349602460861206},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.4201701879501343},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36257702112197876},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2887188792228699}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292413949966431},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7843427658081055},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7757136821746826},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6702110767364502},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5803855061531067},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4840511679649353},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.47373974323272705},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4492442011833191},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.4349602460861206},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.4201701879501343},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36257702112197876},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2887188792228699},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2567948.2577271","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2567948.2577271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd 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":6,"referenced_works":["https://openalex.org/W1660390307","https://openalex.org/W1929352279","https://openalex.org/W2138662031","https://openalex.org/W2161468532","https://openalex.org/W2911388033","https://openalex.org/W4211026344"],"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/W2095543197","https://openalex.org/W2371838993","https://openalex.org/W2321599862","https://openalex.org/W2066869521"],"abstract_inverted_index":{"The":[0,64,99],"main":[1],"goals":[2],"of":[3,28,48,82,88],"a":[4,24,49,83,86,90,95],"web":[5,36,50,57],"search":[6,37,51,97],"engine":[7],"are":[8,73,113],"quality,":[9],"efficiency,":[10],"and":[11,31,60,66,94,107],"scalability.":[12],"In":[13,39],"this":[14],"tutorial,":[15],"we":[16],"focus":[17],"on":[18,55],"the":[19,29,41,56,80,116],"last":[20],"two":[21],"goals,":[22],"providing":[23],"fairly":[25],"comprehensive":[26],"overview":[27,47],"scalability":[30,65],"efficiency":[32,67],"challenges":[33],"in":[34,70],"large-scale":[35],"engines.":[38],"particular,":[40],"tutorial":[42,100],"provides":[43,108],"an":[44],"in-depth":[45],"architectural":[46],"engine,":[52],"mainly":[53],"focusing":[54],"crawling,":[58],"indexing,":[59],"query":[61],"processing":[62],"components.":[63],"issues":[68],"encountered":[69],"these":[71],"components":[72],"presented":[74],"at":[75,79,103],"four":[76],"different":[77],"granularities:":[78],"level":[81],"single":[84,91],"computer,":[85],"cluster":[87],"computers,":[89],"data":[92],"center,":[93],"multi-center":[96],"engine.":[98],"also":[101],"points":[102],"open":[104],"research":[105],"problems":[106],"recommendations":[109],"to":[110,115],"researchers":[111],"who":[112],"new":[114],"field.":[117]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
