{"id":"https://openalex.org/W2057822303","doi":"https://doi.org/10.1145/1989323.1989452","title":"Web data management","display_name":"Web data management","publication_year":2011,"publication_date":"2011-06-12","ids":{"openalex":"https://openalex.org/W2057822303","doi":"https://doi.org/10.1145/1989323.1989452","mag":"2057822303"},"language":"en","primary_location":{"id":"doi:10.1145/1989323.1989452","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 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/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Cafarella","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067621853","display_name":"Alon Halevy","orcid":"https://orcid.org/0000-0002-8717-7356"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alon Y. Halevy","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2924,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.91079089,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1199","last_page":"1200"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.998199999332428,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.996399998664856,"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":0.8152844905853271},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6596308946609497},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5626320838928223},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4624623954296112},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46216416358947754},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.45200106501579285},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41502341628074646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8152844905853271},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6596308946609497},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5626320838928223},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4624623954296112},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46216416358947754},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.45200106501579285},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41502341628074646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1989323.1989452","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.366.4429","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.366.4429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.eecs.umich.edu/~michjc/papers/sigmod902t-cafarella.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"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":17,"referenced_works":["https://openalex.org/W1493490255","https://openalex.org/W1617966546","https://openalex.org/W2013970953","https://openalex.org/W2022166150","https://openalex.org/W2094728533","https://openalex.org/W2108223890","https://openalex.org/W2111869785","https://openalex.org/W2119828234","https://openalex.org/W2137435551","https://openalex.org/W2140602286","https://openalex.org/W2144358319","https://openalex.org/W2146304342","https://openalex.org/W2148540243","https://openalex.org/W2153225416","https://openalex.org/W6629638141","https://openalex.org/W6636631317","https://openalex.org/W6680646450"],"related_works":["https://openalex.org/W2033101018","https://openalex.org/W2099278314","https://openalex.org/W2394886764","https://openalex.org/W2938786841","https://openalex.org/W2282598741","https://openalex.org/W2361540170","https://openalex.org/W1637796940","https://openalex.org/W40856544","https://openalex.org/W2385719512","https://openalex.org/W2335880842"],"abstract_inverted_index":{"Web":[0,48,225],"Data":[1,226],"Management":[2],"(or":[3,201],"WDM)":[4],"refers":[5],"to":[6,154,167,197],"a":[7,112,137,169],"body":[8],"of":[9,17,41,46,57,66,99,117,120,130,140,144,178,186,224],"work":[10,61,121],"concerned":[11],"with":[12,43],"leveraging":[13,136],"the":[14,25,28,44,97,103,125,155,183,204,212,222],"large":[15],"collections":[16,40,65],"structured":[18,67],"data":[19,42,68,180],"that":[20,127,150,181],"can":[21,132],"be":[22,109,133],"extracted":[23,110],"from":[24,102,105],"Web.":[26],"Over":[27],"past":[29],"few":[30],"years,":[31],"several":[32],"research":[33],"and":[34,50,74,79,88,93,95,146,216],"commercial":[35],"efforts":[36],"have":[37],"explored":[38],"these":[39],"goal":[45],"improving":[47],"search":[49,58],"developing":[51],"mechanisms":[52],"for":[53],"surfacing":[54],"different":[55],"kinds":[56,129],"answers.":[59],"This":[60],"has":[62],"leveraged":[63],"(1)":[64],"such":[69,85],"as":[70,86],"HTML":[71],"tables,":[72],"lists":[73],"forms,":[75],"(2)":[76],"recent":[77],"ontologies":[78],"knowledge":[80],"bases":[81],"created":[82,142],"by":[83,135],"crowd-sourcing,":[84],"Wikipedia":[87],"its":[89],"derivatives,":[90],"DBPedia,":[91],"YAGO":[92],"Freebase,":[94],"(3)":[96],"collection":[98,139],"text":[100],"documents":[101],"Web,":[104],"which":[106],"facts":[107],"could":[108],"in":[111,148,221],"domain-independent":[113],"fashion.":[114],"The":[115],"promise":[116],"this":[118],"line":[119],"is":[122,194],"based":[123],"on":[124],"observation":[126],"new":[128],"results":[131],"obtained":[134,218],"huge":[138],"independently":[141],"fragments":[143],"data,":[145],"typically":[147],"ways":[149],"are":[151,206],"wholly":[152],"unrelated":[153],"authors'":[156],"original":[157],"intent.":[158],"For":[159],"example,":[160],"we":[161,173],"might":[162,174],"use":[163],"many":[164,176],"database":[165],"schemas":[166],"compute":[168],"schema":[170],"thesaurus.":[171],"Or":[172],"examine":[175],"spreadsheets":[177],"scientific":[179,189],"reveal":[182],"aggregate":[184],"practice":[185],"an":[187],"entire":[188],"field.":[190],"As":[191],"such,":[192],"WDM":[193],"tightly":[195],"linked":[196],"Web-enabled":[198],"collaboration,":[199],"even":[200],"especially)":[202],"if":[203],"collaborators":[205],"unwitting":[207],"ones.":[208],"We":[209],"will":[210],"cover":[211],"key":[213],"techniques,":[214],"principles":[215],"insights":[217],"so":[219],"far":[220],"area":[223],"Management.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}