{"id":"https://openalex.org/W2156998544","doi":"https://doi.org/10.1145/1807167.1807256","title":"Optimizing content freshness of relations extracted from the web using keyword search","display_name":"Optimizing content freshness of relations extracted from the web using keyword search","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2156998544","doi":"https://doi.org/10.1145/1807167.1807256","mag":"2156998544"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807256","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","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/A5103075868","display_name":"Mohan Yang","orcid":"https://orcid.org/0000-0002-6886-0256"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mohan Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, and Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, and Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369","https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063351917","display_name":"Haixun Wang","orcid":"https://orcid.org/0009-0007-0773-7004"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haixun Wang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109215836","display_name":"Lipyeow Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lipyeow Lim","raw_affiliation_strings":["University of Hawaii at Manoa, Honolulu, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hawaii at Manoa, Honolulu, USA","institution_ids":["https://openalex.org/I117965899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101559441","display_name":"Min Wang","orcid":"https://orcid.org/0000-0001-6771-8947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Wang","raw_affiliation_strings":["HP Labs China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HP Labs China, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4273,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89318765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"819","last_page":"830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9957000017166138,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9853000044822693,"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":0.8478173017501831},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.5434179902076721},{"id":"https://openalex.org/keywords/keyword-density","display_name":"Keyword density","score":0.4931175410747528},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.4904443919658661},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.48971226811408997},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48154690861701965},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.4708865284919739},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4423713684082031},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.4421539902687073},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4142628014087677},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3507818281650543},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.32733583450317383},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.2683055102825165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478173017501831},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.5434179902076721},{"id":"https://openalex.org/C57560718","wikidata":"https://www.wikidata.org/wiki/Q125627","display_name":"Keyword density","level":3,"score":0.4931175410747528},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.4904443919658661},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.48971226811408997},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48154690861701965},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.4708865284919739},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4423713684082031},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.4421539902687073},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4142628014087677},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3507818281650543},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.32733583450317383},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2683055102825165},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1807167.1807256","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.396.8330","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.396.8330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2.hawaii.edu/~lipyeow/pub/sigmod10-contentfreshness.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1490501152","https://openalex.org/W1983454294","https://openalex.org/W1987272746","https://openalex.org/W2046209754","https://openalex.org/W2049898997","https://openalex.org/W2062021443","https://openalex.org/W2081948558","https://openalex.org/W2110034127","https://openalex.org/W2120642948","https://openalex.org/W2123159709","https://openalex.org/W2135252439","https://openalex.org/W2138310207","https://openalex.org/W2141461755","https://openalex.org/W2145102654","https://openalex.org/W2148738951","https://openalex.org/W2165676441","https://openalex.org/W2170188121","https://openalex.org/W2611804663","https://openalex.org/W4300550233","https://openalex.org/W6681291871","https://openalex.org/W6685116542","https://openalex.org/W6844382842"],"related_works":["https://openalex.org/W1996092152","https://openalex.org/W2127536142","https://openalex.org/W1987272746","https://openalex.org/W1976624301","https://openalex.org/W2056598903","https://openalex.org/W2556041162","https://openalex.org/W2182172489","https://openalex.org/W2551693437","https://openalex.org/W2038378248","https://openalex.org/W2331559947","https://openalex.org/W2319012534","https://openalex.org/W1968443587","https://openalex.org/W2551304595","https://openalex.org/W2151932833","https://openalex.org/W2182737792","https://openalex.org/W2070131511","https://openalex.org/W2097971134","https://openalex.org/W2150337951","https://openalex.org/W2334228183","https://openalex.org/W3137674770"],"abstract_inverted_index":{"An":[0],"increasing":[1],"number":[2],"of":[3,18,50,103,126,138,153,184,192],"applications":[4,13,64],"operate":[5],"on":[6,32,73,84,113,174],"data":[7,21,27,31,54,95,105,110,128,159,202],"obtained":[8],"from":[9,93],"the":[10,19,30,33,40,51,85,98,101,104,124,127,136,185,190],"Web.":[11],"These":[12],"typically":[14],"maintain":[15],"local":[16,41,186],"copies":[17],"web":[20,66,69,78,154],"to":[22,108,181],"avoid":[23],"network":[24],"latency":[25],"in":[26,90],"accesses.":[28],"As":[29],"Web":[34],"evolves,":[35],"it":[36],"is":[37,48,71,160],"critical":[38],"that":[39,122,146],"copy":[42],"be":[43],"kept":[44],"up-to-date.":[45],"Data":[46],"freshness":[47,149,183],"one":[49],"most":[52],"important":[53],"quality":[55],"issues,":[56],"and":[57,116,141,168],"has":[58],"been":[59],"extensively":[60],"studied":[61],"for":[62,200],"various":[63],"including":[65],"crawling.":[67],"However,":[68],"crawling":[70],"focused":[72],"obtaining":[74],"as":[75,80,177],"many":[76],"raw":[77],"pages":[79],"possible.":[81],"Our":[82],"applications,":[83],"other":[86],"hand,":[87],"are":[88,119],"interested":[89],"specific":[91,94],"content":[92,99,139,148,182],"sources.":[96],"Knowing":[97],"or":[100],"semantics":[102],"enables":[106],"us":[107],"differentiate":[109],"items":[111],"based":[112,173],"their":[114,175,179],"importance":[115],"volatility,":[117],"which":[118],"key":[120],"factors":[121],"impact":[123],"design":[125],"synchronization":[129],"strategy.":[130],"In":[131],"this":[132],"work,":[133],"we":[134,157,169],"formulate":[135],"concept":[137],"freshness,":[140],"present":[142],"a":[143,163],"novel":[144],"approach":[145,194],"maintains":[147],"with":[150,196],"least":[151],"amount":[152],"communication.":[155],"Specifically,":[156],"assume":[158],"accessible":[161],"through":[162],"general":[164],"keyword":[165,171],"search":[166],"interface,":[167],"form":[170],"queries":[172],"selectivity,":[176],"well":[178],"contribution":[180],"copy.":[187],"Experiments":[188],"show":[189],"effectiveness":[191],"our":[193],"compared":[195],"several":[197],"naive":[198],"methods":[199],"keeping":[201],"fresh.":[203]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
