{"id":"https://openalex.org/W2271728057","doi":"https://doi.org/10.1145/2736277.2741100","title":"Essential Web Pages Are Easy to Find","display_name":"Essential Web Pages Are Easy to Find","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W2271728057","doi":"https://doi.org/10.1145/2736277.2741100","mag":"2271728057"},"language":"en","primary_location":{"id":"doi:10.1145/2736277.2741100","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th 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":"middle","author":{"id":"https://openalex.org/A5038842358","display_name":"Paolo Boldi","orcid":"https://orcid.org/0000-0002-8297-6255"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Boldi","raw_affiliation_strings":["Universit\u00e0 degli Studi di Milano, Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 degli Studi di Milano, Milano, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078401676","display_name":"Flavio Chierichetti","orcid":"https://orcid.org/0000-0001-8261-9058"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Flavio Chierichetti","raw_affiliation_strings":["Sapienza University of Rome, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Roma, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076204770"],"corresponding_institution_ids":["https://openalex.org/I2800095910"],"apc_list":null,"apc_paid":null,"fwci":1.1487,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.79849571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9979000091552734,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9979000091552734,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9962000250816345,"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/T12288","display_name":"Optimization and Search Problems","score":0.9958999752998352,"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":0.7648193836212158},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5894237756729126},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5844398140907288},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.5570034980773926},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.5432433485984802},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5428547859191895},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4897780418395996},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.465924471616745},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44410985708236694},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.41831305623054504},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37098973989486694},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27294373512268066},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21331331133842468},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18789184093475342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11616471409797668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648193836212158},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5894237756729126},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5844398140907288},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.5570034980773926},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.5432433485984802},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5428547859191895},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4897780418395996},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.465924471616745},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44410985708236694},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.41831305623054504},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37098973989486694},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27294373512268066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21331331133842468},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18789184093475342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11616471409797668},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2736277.2741100","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2736277.2741100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/877846","is_oa":false,"landing_page_url":"http://hdl.handle.net/11573/877846","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W168093571","https://openalex.org/W1483313504","https://openalex.org/W1495124840","https://openalex.org/W1660390307","https://openalex.org/W1969840591","https://openalex.org/W1990129631","https://openalex.org/W1990313671","https://openalex.org/W1994727615","https://openalex.org/W2000042664","https://openalex.org/W2002022506","https://openalex.org/W2002788131","https://openalex.org/W2006997130","https://openalex.org/W2011039300","https://openalex.org/W2061820396","https://openalex.org/W2065487600","https://openalex.org/W2104588805","https://openalex.org/W2108858998","https://openalex.org/W2111772229","https://openalex.org/W2119012894","https://openalex.org/W2148372359","https://openalex.org/W2160555926","https://openalex.org/W2293756138","https://openalex.org/W2476096155","https://openalex.org/W2611804663","https://openalex.org/W3103362336","https://openalex.org/W4249318479","https://openalex.org/W6844382842"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3204684126","https://openalex.org/W3117290964","https://openalex.org/W1594413663","https://openalex.org/W2163115662","https://openalex.org/W189401716","https://openalex.org/W2898570308","https://openalex.org/W2019216770","https://openalex.org/W2574250816","https://openalex.org/W2544904580"],"abstract_inverted_index":{"In":[0],"this":[1,134,153],"paper":[2],"we":[3,59,85],"address":[4],"the":[5,9,26,41,62,83,91,96,117,120,136,160,182,187,192],"problem":[6,63],"of":[7,43,54,67,79,133,159,172,181,186,191],"estimating":[8],"index":[10],"size":[11],"needed":[12],"by":[13,24],"web":[14,45,173],"search":[15,202],"engines":[16],"to":[17,75,140,149,156,177],"answer":[18],"as":[19,22,47,64,214],"many":[20],"queries":[21,56,183],"possible":[23,37],"exploiting":[25],"marked":[27],"difference":[28],"between":[29],"query":[30],"and":[31,204],"click":[32,162],"frequencies.":[33],"We":[34,151],"provide":[35,86,141],"a":[36,51,65,77,87,103,124,169,178,215],"formal":[38],"definition":[39],"for":[40,112,115],"notion":[42],"essential":[44],"pages":[46,174,188],"those":[48],"that":[49,143,168,223],"cover":[50,99],"large":[52,179],"fraction":[53,180],"distinct":[55],"---":[57,213],"i.e.,":[58],"look":[60],"at":[61,102,123],"version":[66],"MaxCover.":[68],"Although":[69],"in":[70,129,199,206],"general":[71,211],"MaxCover":[72,235],"is":[73,138],"approximable":[74],"within":[76],"factor":[78,106],"1-1/e":[80],"~0.632":[81],"from":[82,107,119],"optimum,":[84],"condition":[88],"under":[89],"which":[90],"greedy":[92],"algorithm":[93,137,225],"does":[94],"find":[95],"actual":[97],"best":[98],"(or":[100,114],"remains":[101],"known":[104],"bounded":[105],"it).":[108],"The":[109],"extra":[110],"check":[111],"optimality":[113],"bounding":[116],"ratio":[118],"optimum)":[121],"comes":[122],"negligible":[125],"algorithmic":[126],"cost.":[127],"Moreover,":[128],"most":[130],"practical":[131],"instances":[132],"problem,":[135],"able":[139],"solutions":[142],"are":[144],"provably":[145],"optimal,":[146],"or":[147],"close":[148],"optimal.":[150],"relate":[152],"observed":[154],"phenomenon":[155],"some":[157],"properties":[158],"queries'":[161],"graph.":[163],"Our":[164,194],"experimental":[165,220],"results":[166],"confirm":[167],"small":[170],"number":[171],"can":[175,196],"respond":[176],"(e.g.,":[184],"0.4%":[185],"answers":[189],"20%":[190],"queries).":[193],"approach":[195],"be":[197],"used":[198],"several":[200],"related":[201],"applications,":[203],"has":[205,226],"fact":[207],"an":[208],"even":[209],"more":[210],"appeal":[212],"first":[216],"example,":[217],"our":[218,224],"preliminary":[219],"study":[221],"confirms":[222],"extremely":[227],"good":[228],"performances":[229],"on":[230],"other":[231],"(social":[232],"network":[233],"based)":[234],"instances.":[236]},"counts_by_year":[{"year":2024,"cited_by_count":20},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}