{"id":"https://openalex.org/W4367310562","doi":"https://doi.org/10.1145/3543873.3587331","title":"The Web Data Commons Schema.org Data Set Series","display_name":"The Web Data Commons Schema.org Data Set Series","publication_year":2023,"publication_date":"2023-04-28","ids":{"openalex":"https://openalex.org/W4367310562","doi":"https://doi.org/10.1145/3543873.3587331"},"language":"en","primary_location":{"id":"doi:10.1145/3543873.3587331","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543873.3587331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"conference-paper","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/A5062326789","display_name":"Alexander Brinkmann","orcid":"https://orcid.org/0000-0002-9379-2048"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Brinkmann","raw_affiliation_strings":["University of Mannheim, Germany"],"raw_orcid":"https://orcid.org/0000-0002-9379-2048","affiliations":[{"raw_affiliation_string":"University of Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010968230","display_name":"Anna Primpeli","orcid":"https://orcid.org/0000-0002-1783-2482"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anna Primpeli","raw_affiliation_strings":["University of Mannheim, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1783-2482","affiliations":[{"raw_affiliation_string":"University of Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076876024","display_name":"Christian Bizer","orcid":"https://orcid.org/0000-0003-2367-0237"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Bizer","raw_affiliation_strings":["University of Mannheim, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2367-0237","affiliations":[{"raw_affiliation_string":"University of Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"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":0.9986000061035156,"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/T11719","display_name":"Data Quality and Management","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9930999875068665,"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":0.8007300496101379},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6553919911384583},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5678893327713013},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5202054381370544},{"id":"https://openalex.org/keywords/conceptual-schema","display_name":"Conceptual schema","score":0.46716320514678955},{"id":"https://openalex.org/keywords/commons","display_name":"Commons","score":0.41895434260368347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007300496101379},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6553919911384583},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5678893327713013},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5202054381370544},{"id":"https://openalex.org/C29275276","wikidata":"https://www.wikidata.org/wiki/Q2268965","display_name":"Conceptual schema","level":3,"score":0.46716320514678955},{"id":"https://openalex.org/C49427245","wikidata":"https://www.wikidata.org/wiki/Q9828451","display_name":"Commons","level":2,"score":0.41895434260368347},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C165611974","wikidata":"https://www.wikidata.org/wiki/Q5531015","display_name":"Gender schema theory","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3543873.3587331","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543873.3587331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:64408","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.1145/3543873.3587331","pdf_url":null,"source":{"id":"https://openalex.org/S4377196315","display_name":"MADOC (University of Mannheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177802217","host_organization_name":"University of Mannheim","host_organization_lineage":["https://openalex.org/I177802217"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.6299999952316284}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309381","display_name":"Emory University","ror":"https://ror.org/03czfpz43"},{"id":"https://openalex.org/F4320309532","display_name":"Syracuse University","ror":"https://ror.org/025r5qe02"},{"id":"https://openalex.org/F4320309622","display_name":"Harvard University","ror":"https://ror.org/03vek6s52"},{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"},{"id":"https://openalex.org/F4320310017","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97"},{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"},{"id":"https://openalex.org/F4320310419","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231"},{"id":"https://openalex.org/F4320310846","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903"},{"id":"https://openalex.org/F4320316370","display_name":"Universit\u00e4t Passau","ror":"https://ror.org/05ydjnb78"},{"id":"https://openalex.org/F4320319918","display_name":"York University","ror":"https://ror.org/05fq50484"},{"id":"https://openalex.org/F4320320337","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53"},{"id":"https://openalex.org/F4320320966","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12"},{"id":"https://openalex.org/F4320320967","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041"},{"id":"https://openalex.org/F4320320972","display_name":"RMIT University","ror":"https://ror.org/04ttjf776"},{"id":"https://openalex.org/F4320322225","display_name":"Link\u00f6pings Universitet","ror":"https://ror.org/05ynxx418"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320322449","display_name":"Tongji University","ror":"https://ror.org/03rc6as71"},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"},{"id":"https://openalex.org/F4320323322","display_name":"Universit\u00e4t des Saarlandes","ror":"https://ror.org/01jdpyv68"},{"id":"https://openalex.org/F4320323610","display_name":"Central European University","ror":"https://ror.org/02zx40v98"},{"id":"https://openalex.org/F4320323900","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95"},{"id":"https://openalex.org/F4320324136","display_name":"Universit\u00e0 della Calabria","ror":"https://ror.org/02rc97e94"},{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"id":"https://openalex.org/F4320324663","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49"},{"id":"https://openalex.org/F4320328656","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320332749","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W155236017","https://openalex.org/W2024233596","https://openalex.org/W2061760029","https://openalex.org/W2196674927","https://openalex.org/W2238917604","https://openalex.org/W2806096072","https://openalex.org/W2914263187"],"related_works":["https://openalex.org/W629399385","https://openalex.org/W4248994601","https://openalex.org/W39310976","https://openalex.org/W1985157031","https://openalex.org/W2360992999","https://openalex.org/W101905311","https://openalex.org/W3163421923","https://openalex.org/W10742908","https://openalex.org/W2151469757","https://openalex.org/W2368746252"],"abstract_inverted_index":{"Millions":[0],"of":[1,61,74,109,130,153,156,171],"websites":[2],"have":[3],"started":[4],"to":[5],"annotate":[6],"structured":[7],"data":[8,41,54,64,98,132,162,187],"within":[9],"their":[10],"HTML":[11],"pages":[12],"using":[13],"the":[14,43,52,59,62,71,97,102,106,113,116,124,154,157,169,175,180],"schema.org":[15,22,40,63,110,161,172],"vocabulary.":[16],"Popular":[17],"entity":[18,84],"types":[19],"annotated":[20],"with":[21],"terms":[23],"are":[24,182],"products,":[25],"local":[26],"businesses,":[27],"events,":[28],"and":[29,50,177],"job":[30,141],"postings.":[31],"The":[32,67,83],"Web":[33,94,114,158,176],"Data":[34,159],"Commons":[35,160],"project":[36],"has":[37],"been":[38],"extracting":[39],"from":[42,87],"Common":[44],"Crawl":[45],"every":[46],"year":[47],"since":[48],"2013":[49],"offers":[51],"extracted":[53],"for":[55,104,133,188],"public":[56],"download":[57],"in":[58,70,168],"form":[60],"set":[65,99,163],"series.":[66,164],"latest":[68],"release":[69],"series":[72,100],"consists":[73],"106":[75],"billion":[76,81],"RDF":[77],"quads":[78],"describing":[79],"3.1":[80],"entities.":[82],"descriptions":[85],"originate":[86],"12.8":[88],"million":[89],"different":[90],"websites.":[91],"From":[92,119],"a":[93,120,127],"Science":[95],"perspective,":[96,123],"lays":[101],"foundation":[103],"analyzing":[105],"adoption":[107,170],"process":[108],"annotations":[111,125,173,181],"on":[112,174],"over":[115],"past":[117],"decade.":[118],"machine":[121,189],"learning":[122,190],"provide":[126],"large":[128],"pool":[129],"training":[131,186],"tasks":[134],"such":[135],"as":[136,185],"product":[137,139],"matching,":[138],"or":[140,145],"categorization,":[142],"information":[143],"extraction,":[144],"question":[146],"answering.":[147],"This":[148],"poster":[149],"gives":[150],"an":[151],"overview":[152],"content":[155],"It":[165],"highlights":[166],"trends":[167],"discusses":[178],"how":[179],"being":[183],"used":[184],"applications.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
