{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T09:18:28Z","timestamp":1774430308594,"version":"3.50.1"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. Comput. Sci. Technol."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s11390-021-1344-6","type":"journal-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T14:03:15Z","timestamp":1628690595000},"page":"806-821","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Impacts of Dirty Data on Classification and Clustering Models: An Experimental Evaluation"],"prefix":"10.1007","volume":"36","author":[{"given":"Zhi-Xin","family":"Qi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong-Zhi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"An-Jie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,30]]},"reference":[{"key":"1344_CR1","doi-asserted-by":"publisher","unstructured":"Beskales G, Ilyas I F, Golab L, Galiullin A. On the relative trust between inconsistent data and inaccurate constraints. In Proc. the 29th IEEE Int. Conf. Data Engineering, Apr. 2013, pp.541-552. https:\/\/doi.org\/10.1109\/ICDE.2013.6544854.","DOI":"10.1109\/ICDE.2013.6544854"},{"key":"1344_CR2","doi-asserted-by":"publisher","unstructured":"Chu X, Ilyas I F, Papotti P. Holistic data cleaning: Putting violations into context. In Proc. the 29th IEEE Int. Conf. Data Engineering, Apr. 2013, pp.458-469. https:\/\/doi.org\/10.1109\/ICDE.2013.6544847.","DOI":"10.1109\/ICDE.2013.6544847"},{"key":"1344_CR3","doi-asserted-by":"publisher","unstructured":"Chu X, Morcos J, Ilyas I F, Ouzzani M, Papotti P, Tang N, Ye Y. KATARA: A data cleaning system powered by knowledge bases and crowdsourcing. In Proc. the 36th ACM Int. Conf. Management of Data, May 2015, pp.1247-1261. https:\/\/doi.org\/10.1145\/2723372.2749431.","DOI":"10.1145\/2723372.2749431"},{"key":"1344_CR4","doi-asserted-by":"publisher","unstructured":"Hao S, Tang N, Li G, Li J. Cleaning relations using knowledge bases. In Proc. the 33rd IEEE Int. Conf. Data Engineering, Apr. 2017, pp.933-944. https:\/\/doi.org\/10.1109\/ICDE.2017.141.","DOI":"10.1109\/ICDE.2017.141"},{"key":"1344_CR5","doi-asserted-by":"publisher","unstructured":"Wang J, Kraska T, Franklin M J, Feng J. CrowdER: Crowdsourcing entity resolution. Proceedings of the VLDB Endowment, 2012, 5(11): 1483-1494. https:\/\/doi.org\/10.14778\/2350229.2350263.","DOI":"10.14778\/2350229.2350263"},{"key":"1344_CR6","doi-asserted-by":"publisher","unstructured":"Dallachiesa M, Ebaid A, Eldawy A, Elmagarmid A, Ilyas I F, Ouzzani M, Tang N. NADEEF: A commodity data cleaning system. In Proc. the 34th ACM Int. Conf. Management of Data, Jun. 2013, pp.541-552. https:\/\/doi.org\/10.1145\/2463676.2465327.","DOI":"10.1145\/2463676.2465327"},{"key":"1344_CR7","doi-asserted-by":"publisher","unstructured":"Gamberger D, Lavra\u010d N. Conditions for Occam\u2019s razor applicability and noise elimination. In Proc. the 9th Springer Eur. Conf. Machine Learning, Apr. 1997, pp.108-123. https:\/\/doi.org\/10.1007\/3-540-62858-4_76.","DOI":"10.1007\/3-540-62858-4_76"},{"issue":"2","key":"1344_CR8","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/s00521-009-0295-6","volume":"19","author":"PJ Garc\u00eda-Laencina","year":"2010","unstructured":"Garc\u00eda-Laencina P J, Sancho-G\u00f3mez J L, Figueiras-Vidal A R. Pattern classification with missing data: A review. Neural Computing and Applications, 2010, 19(2): 263-282. https:\/\/doi.org\/10.1007\/s00521-009-0295-6.","journal-title":"Neural Computing and Applications"},{"key":"1344_CR9","doi-asserted-by":"publisher","unstructured":"Lim S. Cleansing noisy city names in spatial data mining. In Proc. the 2010 Int. Conf. Information Science and Applications, Apr. 2010. https:\/\/doi.org\/10.1109\/ICISA.2010.5480390.","DOI":"10.1109\/ICISA.2010.5480390"},{"key":"1344_CR10","doi-asserted-by":"publisher","unstructured":"Fr\u00e9nay B, Verleysen M. Classification in the presence of label noise: A survey. IEEE Trans. Neural Networks and Learning Systems, 2013, 25(5): 845-869. https:\/\/doi.org\/10.1109\/TNNLS.2013.2292894.","DOI":"10.1109\/TNNLS.2013.2292894"},{"issue":"3","key":"1344_CR11","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s10462-004-0751-8","volume":"22","author":"X Zhu","year":"2004","unstructured":"Zhu X, Wu X. Class noise vs. attribute noise: A quantitative study. Artificial Intelligence Review, 2004, 22(3): 177-210. https:\/\/doi.org\/10.1007\/s10462-004-0751-8.","journal-title":"Artificial Intelligence Review"},{"key":"1344_CR12","doi-asserted-by":"publisher","unstructured":"Song S, Li C, Zhang X. Turn waste into wealth: On simultaneous clustering and cleaning over dirty data. In Proc. the 21st ACM Int. Conf. Knowledge Discovery and Data Mining, Aug. 2015, pp.1115-1124. https:\/\/doi.org\/10.1145\/2783258.2783317.","DOI":"10.1145\/2783258.2783317"},{"key":"1344_CR13","doi-asserted-by":"publisher","unstructured":"Caruana R, Niculescu-Mizil A. An empirical comparison of supervised learning algorithms. In Proc. the 23rd ACM Int. Conf. Machine Learning, Jun. 2006, pp.161-168. https:\/\/doi.org\/10.1145\/1143844.1143865.","DOI":"10.1145\/1143844.1143865"},{"key":"1344_CR14","doi-asserted-by":"publisher","unstructured":"Caruana R, Karampatziakis N, Yessenalina A. An empirical evaluation of supervised learning in high dimensions. In Proc. the 25th ACM Int. Conf. Machine Learning, Jul. 2008, pp.96-103. https:\/\/doi.org\/10.1145\/1390156.1390169.","DOI":"10.1145\/1390156.1390169"},{"key":"1344_CR15","doi-asserted-by":"publisher","unstructured":"Ghotra B, McIntosh S, Hassan A E. Revisiting the impact of classification techniques on the performance of defect prediction models. In Proc. the 37th IEEE\/ACM Int. Conf. Software Engineering, May 2015, pp.789-800. https:\/\/doi.org\/10.1109\/ICSE.2015.91.","DOI":"10.1109\/ICSE.2015.91"},{"issue":"3","key":"1344_CR16","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/s10462-015-9446-6","volume":"45","author":"K Kirchner","year":"2016","unstructured":"Kirchner K, Zec J, Deliba\u0161i\u0107 B. Facilitating data preprocessing by a generic framework: A proposal for clustering. Artificial Intelligence Review, 2016, 45(3): 271-297. https:\/\/doi.org\/10.1007\/s10462-015-9446-6.","journal-title":"Artificial Intelligence Review"},{"key":"1344_CR17","doi-asserted-by":"publisher","unstructured":"Sidi F, Panahy P H S, Affendey L S, Jabar M A, Ibrahim H, Mustapha A. Data quality: A survey of data quality dimensions. In Proc. the 2nd IEEE Int. Conf. Information Retrieval and Knowledge Management, Mar. 2012, pp.300-304. https:\/\/doi.org\/10.1109\/InfRKM.2012.6204995.","DOI":"10.1109\/InfRKM.2012.6204995"},{"key":"1344_CR18","doi-asserted-by":"publisher","unstructured":"Fan W, Geerts F. Capturing missing tuples and missing values. In Proc. the 29th ACM SIGMOD-SIGACT-SIGART Symp. Principles of Database Systems, Jun. 2010, pp.169-178. https:\/\/doi.org\/10.1145\/1807085.1807109.","DOI":"10.1145\/1807085.1807109"},{"key":"1344_CR19","doi-asserted-by":"publisher","unstructured":"Getoor L, Machanavajjhala A. Entity resolution: Theory, practice & open challenges. Proceedings of the VLDB Endowment, 2012, 5(12): 2018-2019. https:\/\/doi.org\/10.14778\/2367502.2367564.","DOI":"10.14778\/2367502.2367564"},{"key":"1344_CR20","doi-asserted-by":"publisher","unstructured":"Arocena P C, Glavic B, Mecca G, Miller R J, Papotti P, Santoro D. Messing up with BART: Error generation for evaluating data-cleaning algorithms. Proceedings of the VLDB Endowment, 2015, 9(2): 36-47. https:\/\/doi.org\/10.14778\/2850578.2850579.","DOI":"10.14778\/2850578.2850579"}],"container-title":["Journal of Computer Science and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-021-1344-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11390-021-1344-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-021-1344-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T14:20:18Z","timestamp":1628691618000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11390-021-1344-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":20,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["1344"],"URL":"https:\/\/doi.org\/10.1007\/s11390-021-1344-6","relation":{},"ISSN":["1000-9000","1860-4749"],"issn-type":[{"value":"1000-9000","type":"print"},{"value":"1860-4749","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]},"assertion":[{"value":"31 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}