{"id":"https://openalex.org/W2924113343","doi":"https://doi.org/10.1145/3308560.3316757","title":"A Graph-Structured Dataset for Wikipedia Research","display_name":"A Graph-Structured Dataset for Wikipedia Research","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2924113343","doi":"https://doi.org/10.1145/3308560.3316757","mag":"2924113343"},"language":"en","primary_location":{"id":"doi:10.1145/3308560.3316757","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308560.3316757","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of The 2019 World Wide Web Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3308560.3316757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nicolas Aspert","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Nicolas Aspert","raw_affiliation_strings":["LTS2, EPFL, Station 11, CH-1015 Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"LTS2, EPFL, Station 11, CH-1015 Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Volodymyr Miz","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Volodymyr Miz","raw_affiliation_strings":["LTS2, EPFL, Station 11, CH-1015 Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"LTS2, EPFL, Station 11, CH-1015 Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Benjamin Ricaud","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Benjamin Ricaud","raw_affiliation_strings":["LTS2, EPFL, Station 11, CH-1015 Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"LTS2, EPFL, Station 11, CH-1015 Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":null,"display_name":"Pierre Vandergheynst","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Pierre Vandergheynst","raw_affiliation_strings":["LTS2, EPFL, Station 11, CH-1015 Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"LTS2, EPFL, Station 11, CH-1015 Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":1.4554,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85396147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1188","last_page":"1193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9269999861717224,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5367000102996826},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48410001397132874},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4034000039100647},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.39500001072883606},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.30799999833106995},{"id":"https://openalex.org/keywords/tag-cloud","display_name":"Tag cloud","score":0.3028999865055084},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.3027999997138977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233999967575073},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5516999959945679},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4885999858379364},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48829999566078186},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C26983874","wikidata":"https://www.wikidata.org/wiki/Q263864","display_name":"Tag cloud","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C4727928","wikidata":"https://www.wikidata.org/wiki/Q17164759","display_name":"Social network (sociolinguistics)","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C114713312","wikidata":"https://www.wikidata.org/wiki/Q7551269","display_name":"Social network analysis","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3308560.3316757","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308560.3316757","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of The 2019 World Wide Web Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.08597","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.08597","pdf_url":"https://arxiv.org/pdf/1903.08597","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:infoscience.epfl.ch:264888","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/264888","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"},{"id":"pmh:oai:zenodo.org:4041647","is_oa":true,"landing_page_url":"https://zenodo.org/record/4041647","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"doi:10.1145/3308560.3316757","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3308560.3316757","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of The 2019 World Wide Web Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1503870525","display_name":null,"funder_award_id":"642685","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2001806450","display_name":null,"funder_award_id":"H2020-MSCA-ITN","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2678857217","display_name":null,"funder_award_id":"H2020-MSCA-ITN-2014","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3345895242","display_name":null,"funder_award_id":"H2020-MSCA","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6076719424","display_name":null,"funder_award_id":"H2020-MSCA-ITN-2014","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7370382080","display_name":null,"funder_award_id":"642685","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7984235579","display_name":null,"funder_award_id":"H2020-MSCA-ITN","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G8512683158","display_name":null,"funder_award_id":"H2020-MSCA","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1755289444","https://openalex.org/W2012967345","https://openalex.org/W2043253351","https://openalex.org/W2116021465","https://openalex.org/W2743418339","https://openalex.org/W2913991297","https://openalex.org/W2963214893"],"related_works":[],"abstract_inverted_index":{"Wikipedia":[0,35,93,140],"is":[1,71,95,113,129],"a":[2,17,48,62,120,137],"rich":[3],"and":[4,43,59,83,101],"invaluable":[5],"source":[6],"of":[7,21,54,92,103,124,139,146,148],"information.":[8],"Its":[9],"central":[10],"place":[11],"on":[12],"the":[13,51,55,90,99,108,111,131],"Web":[14],"makes":[15,98],"it":[16],"particularly":[18,72],"interesting":[19],"object":[20],"study":[22,37],"for":[23,65],"scientists.":[24],"Researchers":[25],"from":[26,142],"different":[27],"domains":[28,76],"used":[29],"various":[30],"complex":[31],"datasets":[32],"related":[33],"to":[34,36,115,119,144],"language,":[38],"social":[39],"behavior,":[40],"knowledge":[41],"organization,":[42],"network":[44],"theory.":[45],"While":[46],"being":[47],"scientific":[49,75],"treasure,":[50],"large":[52],"size":[53,91],"dataset":[56],"hinders":[57],"pre-processing":[58],"may":[60,79],"be":[61,81],"challenging":[63],"obstacle":[64],"potential":[66],"new":[67],"studies.":[68],"This":[69],"issue":[70],"acute":[73],"in":[74],"where":[77],"researchers":[78,135],"not":[80],"technically":[82],"data":[84],"processing":[85],"savvy.":[86],"On":[87,107],"one":[88],"hand,":[89,110],"dumps":[94],"large.":[96],"It":[97],"parsing":[100],"extraction":[102],"relevant":[104],"information":[105],"cumbersome.":[106],"other":[109],"API":[112],"straightforward":[114],"use":[116],"but":[117,150],"restricted":[118],"relatively":[121],"small":[122],"number":[123],"requests.":[125],"The":[126],"middle":[127],"ground":[128],"at":[130,156],"mesoscopic":[132],"scale,":[133],"when":[134],"need":[136],"subset":[138],"ranging":[141],"thousands":[143,147],"hundreds":[145],"pages":[149],"there":[151],"exists":[152],"no":[153],"efficient":[154],"solution":[155],"this":[157],"scale.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-04-01T00:00:00"}
