{"id":"https://openalex.org/W4255845876","doi":"https://doi.org/10.1145/2911451.2914808","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":2016,"publication_date":"2016-07-07","ids":{"openalex":"https://openalex.org/W4255845876","doi":"https://doi.org/10.1145/2911451.2914808"},"language":"en","primary_location":{"id":"doi:10.1145/2911451.2914808","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2911451.2914808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval","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/A5015615642","display_name":"B. Barla Cambazo\u011flu","orcid":"https://orcid.org/0000-0003-2192-3819"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"B. Barla Cambazoglu","raw_affiliation_strings":["Independent Researcher, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Independent Researcher, Barcelona, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076204770","display_name":"Ricardo Baeza\u2010Yates","orcid":"https://orcid.org/0000-0003-3208-9778"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]},{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["CL","ES"],"is_corresponding":false,"raw_author_name":"Ricardo Baeza-Yates","raw_affiliation_strings":["Universitat Pompeu Fabra &amp; Universidad de Chile, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra &amp; Universidad de Chile, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558","https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015615642"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.3078,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.96001904,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1223","last_page":"1226"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9969000220298767,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9901999831199646,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8387819528579712},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7854995131492615},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7823458313941956},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.600118100643158},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5950008630752563},{"id":"https://openalex.org/keywords/metasearch-engine","display_name":"Metasearch engine","score":0.5557137727737427},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.5204862952232361},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4680801331996918},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.45722949504852295},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.442444771528244},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41292011737823486},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4014449119567871},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.39378178119659424},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3666849732398987},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35062289237976074},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13929560780525208},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11820206046104431}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8387819528579712},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7854995131492615},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7823458313941956},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.600118100643158},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5950008630752563},{"id":"https://openalex.org/C173979980","wikidata":"https://www.wikidata.org/wiki/Q114106","display_name":"Metasearch engine","level":4,"score":0.5557137727737427},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.5204862952232361},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4680801331996918},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.45722949504852295},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.442444771528244},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41292011737823486},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4014449119567871},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.39378178119659424},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3666849732398987},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35062289237976074},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13929560780525208},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11820206046104431},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2911451.2914808","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2911451.2914808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1613836731","https://openalex.org/W1750001631","https://openalex.org/W1982012874","https://openalex.org/W1984918470","https://openalex.org/W1995857012","https://openalex.org/W2004570439","https://openalex.org/W2019871559","https://openalex.org/W2028083097","https://openalex.org/W2032395777","https://openalex.org/W2042130547","https://openalex.org/W2042808392","https://openalex.org/W2063230099","https://openalex.org/W2070299948","https://openalex.org/W2072156548","https://openalex.org/W2076214367","https://openalex.org/W2082973176","https://openalex.org/W2085922539","https://openalex.org/W2086453025","https://openalex.org/W2089455813","https://openalex.org/W2090913810","https://openalex.org/W2106591686","https://openalex.org/W2106956947","https://openalex.org/W2108278040","https://openalex.org/W2110679325","https://openalex.org/W2114811766","https://openalex.org/W2127536142","https://openalex.org/W2127899914","https://openalex.org/W2128384372","https://openalex.org/W2133628502","https://openalex.org/W2134195052","https://openalex.org/W2137151464","https://openalex.org/W2137250554","https://openalex.org/W2138662031","https://openalex.org/W2139230733","https://openalex.org/W2141257014","https://openalex.org/W2145990704","https://openalex.org/W2154045882","https://openalex.org/W2157008678","https://openalex.org/W2161468532","https://openalex.org/W2167493836","https://openalex.org/W2171255928","https://openalex.org/W2243366197","https://openalex.org/W2295141584","https://openalex.org/W2342269870","https://openalex.org/W2911388033","https://openalex.org/W4211026344","https://openalex.org/W4214835284","https://openalex.org/W6640236718"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2379145789","https://openalex.org/W2095543197","https://openalex.org/W2371838993","https://openalex.org/W2538203441","https://openalex.org/W2406811307","https://openalex.org/W2363322605","https://openalex.org/W4256136669","https://openalex.org/W2154792254","https://openalex.org/W2058374187"],"abstract_inverted_index":{"Commercial":[0],"web":[1],"search":[2,31,68],"engines":[3,32],"need":[4],"to":[5,15],"process":[6],"thousands":[7],"of":[8,26,55,66],"queries":[9,17],"every":[10,63],"second":[11],"and":[12,34,47,53],"provide":[13],"responses":[14],"user":[16,49],"within":[18],"a":[19,24],"few":[20],"hundred":[21],"milliseconds.":[22],"As":[23],"consequence":[25],"these":[27,56],"tight":[28],"performance":[29,60],"constraints,":[30],"construct":[33],"maintain":[35],"very":[36],"large":[37],"computing":[38],"infrastructures":[39,57],"for":[40],"crawling":[41],"the":[42,67],"Web,":[43],"indexing":[44],"discovered":[45],"pages,":[46],"processing":[48],"queries.":[50],"The":[51],"scalability":[52],"efficiency":[54],"require":[58],"careful":[59],"optimizations":[61],"in":[62],"major":[64],"component":[65],"engine.":[69]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
