@article{SHENOY2022100679,
  title = {A study of the quality of Wikidata},
  journal = {Journal of Web Semantics},
  volume = {72},
  pages = {100679},
  year = {2022},
  issn = {1570-8268},
  doi = {10.1016/j.websem.2021.100679},
  url = {https://dgarijo.com/papers/a_study_wikidata_2022.pdf},
  author = {Kartik Shenoy and Filip Ilievski and Daniel Garijo and Daniel Schwabe and Pedro Szekely},
  keywords = {Wikidata, Data quality, Knowledge graphs, Constraints, Crowdsourcing},
  abstract = {Wikidata has been increasingly adopted by many communities for a wide variety of applications, which demand high-quality knowledge to deliver successful results. In this paper, we develop a framework to detect and analyze low-quality statements in Wikidata by shedding light on the current practices exercised by the community. We explore three indicators of data quality in Wikidata, based on: (1) community consensus on the currently recorded knowledge, assuming that statements that have been removed and not added back are implicitly agreed to be of low quality; (2) statements that have been deprecated; and (3) constraint violations in the data. We combine these indicators to detect low-quality statements, revealing challenges with duplicate entities, missing triples, violated type rules, and taxonomic distinctions. Our findings complement ongoing efforts by the Wikidata community to improve data quality, aiming to make it easier for users and editors to find and correct mistakes.}
}

{"_id":"WJhyDGaQP7fMwCdR2","bibbaseid":"shenoy-ilievski-garijo-schwabe-szekely-astudyofthequalityofwikidata-2022","author_short":["Shenoy, K.","Ilievski, F.","Garijo, D.","Schwabe, D.","Szekely, P."],"bibdata":{"bibtype":"article","type":"article","title":"A study of the quality of Wikidata","journal":"Journal of Web Semantics","volume":"72","pages":"100679","year":"2022","issn":"1570-8268","doi":"10.1016/j.websem.2021.100679","url":"https://dgarijo.com/papers/a_study_wikidata_2022.pdf","author":[{"firstnames":["Kartik"],"propositions":[],"lastnames":["Shenoy"],"suffixes":[]},{"firstnames":["Filip"],"propositions":[],"lastnames":["Ilievski"],"suffixes":[]},{"firstnames":["Daniel"],"propositions":[],"lastnames":["Garijo"],"suffixes":[]},{"firstnames":["Daniel"],"propositions":[],"lastnames":["Schwabe"],"suffixes":[]},{"firstnames":["Pedro"],"propositions":[],"lastnames":["Szekely"],"suffixes":[]}],"keywords":"Wikidata, Data quality, Knowledge graphs, Constraints, Crowdsourcing","abstract":"Wikidata has been increasingly adopted by many communities for a wide variety of applications, which demand high-quality knowledge to deliver successful results. In this paper, we develop a framework to detect and analyze low-quality statements in Wikidata by shedding light on the current practices exercised by the community. We explore three indicators of data quality in Wikidata, based on: (1) community consensus on the currently recorded knowledge, assuming that statements that have been removed and not added back are implicitly agreed to be of low quality; (2) statements that have been deprecated; and (3) constraint violations in the data. We combine these indicators to detect low-quality statements, revealing challenges with duplicate entities, missing triples, violated type rules, and taxonomic distinctions. Our findings complement ongoing efforts by the Wikidata community to improve data quality, aiming to make it easier for users and editors to find and correct mistakes.","bibtex":"@article{SHENOY2022100679,\r\n title = {A study of the quality of Wikidata},\r\n journal = {Journal of Web Semantics},\r\n volume = {72},\r\n pages = {100679},\r\n year = {2022},\r\n issn = {1570-8268},\r\n doi = {10.1016/j.websem.2021.100679},\r\n url = {https://dgarijo.com/papers/a_study_wikidata_2022.pdf},\r\n author = {Kartik Shenoy and Filip Ilievski and Daniel Garijo and Daniel Schwabe and Pedro Szekely},\r\n keywords = {Wikidata, Data quality, Knowledge graphs, Constraints, Crowdsourcing},\r\n abstract = {Wikidata has been increasingly adopted by many communities for a wide variety of applications, which demand high-quality knowledge to deliver successful results. In this paper, we develop a framework to detect and analyze low-quality statements in Wikidata by shedding light on the current practices exercised by the community. We explore three indicators of data quality in Wikidata, based on: (1) community consensus on the currently recorded knowledge, assuming that statements that have been removed and not added back are implicitly agreed to be of low quality; (2) statements that have been deprecated; and (3) constraint violations in the data. We combine these indicators to detect low-quality statements, revealing challenges with duplicate entities, missing triples, violated type rules, and taxonomic distinctions. Our findings complement ongoing efforts by the Wikidata community to improve data quality, aiming to make it easier for users and editors to find and correct mistakes.}\r\n}\r\n\r\n","author_short":["Shenoy, K.","Ilievski, F.","Garijo, D.","Schwabe, D.","Szekely, P."],"key":"SHENOY2022100679","id":"SHENOY2022100679","bibbaseid":"shenoy-ilievski-garijo-schwabe-szekely-astudyofthequalityofwikidata-2022","role":"author","urls":{"Paper":"https://dgarijo.com/papers/a_study_wikidata_2022.pdf"},"keyword":["Wikidata","Data quality","Knowledge graphs","Constraints","Crowdsourcing"],"metadata":{"authorlinks":{}},"downloads":2},"bibtype":"article","biburl":"http://dgarijo.com/garijo.bib","dataSources":["2rbi2engWW5WQozKr","R2JGJBRCxupuWD8jt","uQXmfga9QQDTJq9Bx"],"keywords":["wikidata","data quality","knowledge graphs","constraints","crowdsourcing"],"search_terms":["study","quality","wikidata","shenoy","ilievski","garijo","schwabe","szekely"],"title":"A study of the quality of Wikidata","year":2022,"downloads":2}