{"id":"https://openalex.org/W2094305704","doi":"https://doi.org/10.1145/2756406.2756947","title":"Identifying Duplicate and Contradictory Information in Wikipedia","display_name":"Identifying Duplicate and Contradictory Information in Wikipedia","publication_year":2015,"publication_date":"2015-06-12","ids":{"openalex":"https://openalex.org/W2094305704","doi":"https://doi.org/10.1145/2756406.2756947","mag":"2094305704"},"language":"en","primary_location":{"id":"doi:10.1145/2756406.2756947","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2756406.2756947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM/IEEE-CS Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"type":"preprint","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/A5040249762","display_name":"Sarah Weissman","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sarah Weissman","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011635056","display_name":"Samet Ayhan","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samet Ayhan","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078244482","display_name":"Joshua Bradley","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Bradley","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040249762"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":1.9779,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.88991365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9994999766349792,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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/T10028","display_name":"Topic Modeling","score":0.9936000108718872,"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/jaccard-index","display_name":"Jaccard index","score":0.9315118193626404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8106887340545654},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7251551151275635},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.648760199546814},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6371033191680908},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.42840224504470825},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3896867036819458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22592025995254517},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.12812680006027222},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05903136730194092}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.9315118193626404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106887340545654},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7251551151275635},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.648760199546814},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6371033191680908},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.42840224504470825},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3896867036819458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22592025995254517},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.12812680006027222},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05903136730194092},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2756406.2756947","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2756406.2756947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM/IEEE-CS Joint Conference on Digital Libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.750.2020","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.750.2020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1406.1143.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6609948673","display_name":null,"funder_award_id":"IIS-1218043","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1968197683","https://openalex.org/W1972644898","https://openalex.org/W1981053739","https://openalex.org/W1983704604","https://openalex.org/W1986571907","https://openalex.org/W2048395990","https://openalex.org/W2062028408","https://openalex.org/W2085922539","https://openalex.org/W2097776316","https://openalex.org/W2122465391","https://openalex.org/W2132069633","https://openalex.org/W2147717514","https://openalex.org/W2151042663","https://openalex.org/W2151930506","https://openalex.org/W2158342607","https://openalex.org/W2183705191","https://openalex.org/W2752885492","https://openalex.org/W3145128584","https://openalex.org/W6679663036","https://openalex.org/W6682019165","https://openalex.org/W7029321148"],"related_works":["https://openalex.org/W3122011053","https://openalex.org/W2411679502","https://openalex.org/W2183521486","https://openalex.org/W2765264756","https://openalex.org/W2038636168","https://openalex.org/W88463392","https://openalex.org/W3095158916","https://openalex.org/W2349125667","https://openalex.org/W38260586","https://openalex.org/W2529191231"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,53],"identify":[4,35],"sentences":[5,36,82,97],"in":[6,89,106],"Wikipedia":[7,90],"articles":[8],"that":[9,55,98],"are":[10,78],"either":[11],"identical":[12,66,81],"or":[13],"highly":[14],"similar":[15],"by":[16,42],"applying":[17],"techniques":[18],"for":[19],"near-duplicate":[20,96],"detection":[21],"of":[22,32,75],"web":[23],"pages.":[24],"This":[25],"is":[26,91],"accomplished":[27],"with":[28,37],"a":[29,43],"MapReduce":[30],"implementation":[31],"minhash":[33],"to":[34,45,86,103],"high":[38],"Jaccard":[39],"similarity,":[40],"followed":[41],"pass":[44],"generate":[46],"sentence":[47],"clusters.":[48],"Based":[49],"on":[50],"manual":[51],"examination,":[52],"discovered":[54],"these":[56,76],"clusters":[57],"can":[58],"be":[59],"categorized":[60],"into":[61],"six":[62],"different":[63],"types:":[64],"templates,":[65],"sentences,":[67],"copyediting,":[68],"factual":[69],"drift,":[70],"references,":[71],"and":[72,93,95],"other.":[73],"Two":[74],"categories":[77],"particularly":[79],"interesting:":[80],"quantify":[83],"the":[84],"extent":[85],"which":[87],"content":[88],"copied":[92],"pasted,":[94],"state":[99],"contradictory":[100],"facts":[101],"point":[102],"quality":[104],"issues":[105],"Wikipedia.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}