{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T09:18:37Z","timestamp":1774430317238,"version":"3.50.1"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031217524","type":"print"},{"value":"9783031217531","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-21753-1_9","type":"book-chapter","created":{"date-parts":[[2022,11,20]],"date-time":"2022-11-20T10:02:32Z","timestamp":1668938552000},"page":"82-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["On Studying the\u00a0Effect of\u00a0Data Quality on\u00a0Classification Performances"],"prefix":"10.1007","author":[{"given":"Roxane","family":"Jouseau","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S\u00e9bastien","family":"Salva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chafik","family":"Samir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,21]]},"reference":[{"issue":"12","key":"9_CR1","doi-asserted-by":"publisher","first-page":"993","DOI":"10.14778\/2994509.2994518","volume":"9","author":"Z Abedjan","year":"2016","unstructured":"Abedjan, Z., et al.: Detecting data errors: where are we and what needs to be done? Proc. VLDB Endowment 9(12), 993\u20131004 (2016)","journal-title":"Proc. VLDB Endowment"},{"key":"9_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113511","volume":"159","author":"M Ataeyan","year":"2020","unstructured":"Ataeyan, M., Daneshpour, N.: A novel data repairing approach based on constraints and ensemble learning. Expert Syst. Appl. 159, 113511 (2020)","journal-title":"Expert Syst. Appl."},{"key":"9_CR3","unstructured":"Blake, C., Merz, C.: UCI repository of machine learning databases (1998)"},{"key":"9_CR4","unstructured":"Chu, Xu, I.F.I., Papotti, P.: Holistic data cleaning: putting violations into context. In: IEEE 29th International Conference on Data Engineering (ICDE) (2013)"},{"issue":"13","key":"9_CR5","doi-asserted-by":"publisher","first-page":"1605","DOI":"10.14778\/3007263.3007320","volume":"9","author":"X Chu","year":"2016","unstructured":"Chu, X., Ilyas, I.F.: Qualitative data cleaning. Proc. VLDB Endowment 9(13), 1605\u20131608 (2016)","journal-title":"Proc. VLDB Endowment"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Chu, X., Ilyas, I.F., Krishnan, S., Wang, J.: Data cleaning: Overview and emerging challenges. In: SIGMOD Proceedings of the 2016 International Conference on Management of Data, pp. 2201\u20132206 (2016)","DOI":"10.1145\/2882903.2912574"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Chu, X., et al.: Katara: a data cleaning system powered by knowledge bases and crowdsourcing. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, pp. 1247\u20131261 (2015)","DOI":"10.1145\/2723372.2749431"},{"key":"9_CR8","unstructured":"Hynes, N., Sculley, D., Terry, M.: The Data Linter: Lightweight, Automated Sanity Checking for ML Data Sets (2017)"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Jouseau, R., Salva, S., Samir, C.: Technical report for: on studying the effect of data quality on classification performance. Technical report, University of Clermont Auvergne, September 2022. https:\/\/hal.archives-ouvertes.fr\/hal-03782760","DOI":"10.1007\/978-3-031-21753-1_9"},{"key":"9_CR10","unstructured":"Krishnan, S., Franklin, M.J., Goldberg, K., Wu, E.: Boostclean: automated error detection and repair for machine learning. arXiv preprint arXiv:1711.01299 (2017)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Li, P., Rao, X., Blase, J., Zhang, Y., Chu, X., Zhang, C.: CleanML: a study for evaluating the impact of data cleaning on ml classification tasks. In: 36th IEEE International Conference on Data Engineering (ICDE 2020) (virtual) (2021)","DOI":"10.1109\/ICDE51399.2021.00009"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., Vasconcelos, N.: Repair: Removing representation bias by dataset resampling. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9572\u20139581 (2019)","DOI":"10.1109\/CVPR.2019.00980"},{"key":"9_CR13","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"issue":"5","key":"9_CR14","doi-asserted-by":"publisher","first-page":"684","DOI":"10.14778\/3377369.3377377","volume":"13","author":"A Qahtan","year":"2020","unstructured":"Qahtan, A., Tang, N., Ouzzani, M., Cao, Y., Stonebraker, M.: Pattern functional dependencies for data cleaning. Proc. VLDB Endowment 13(5), 684\u2013697 (2020)","journal-title":"Proc. VLDB Endowment"},{"issue":"11","key":"9_CR15","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.14778\/3137628.3137631","volume":"10","author":"T Rekatsinas","year":"2017","unstructured":"Rekatsinas, T., Chu, X., Ilyas, I.F., R\u00e9, C.: HoloClean: holistic data repairs with probabilistic inference. Proc. VLDB Endowment 10(11), 1190\u20131201 (2017)","journal-title":"Proc. VLDB Endowment"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Wu, R., Chaba, S., Sawlani, S., Chu, X., Thirumuruganathan, S.: Zeroer: entity resolution using zero labeled examples. In: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, pp. 1149\u20131164 (2020)","DOI":"10.1145\/3318464.3389743"},{"key":"9_CR17","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms (2017)"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, X., Ji, Y., Nguyen, C., Wang, T.: DeepClean: data cleaning via question asking. In: 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), pp. 283\u2013292 (2018)","DOI":"10.1109\/DSAA.2018.00039"}],"container-title":["Lecture Notes in Computer Science","Intelligent Data Engineering and Automated Learning \u2013 IDEAL 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21753-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:12:47Z","timestamp":1710331967000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21753-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031217524","9783031217531"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21753-1_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"21 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IDEAL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Data Engineering and Automated Learning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Manchester","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ideal2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ideal-conf.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"79","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"52","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"66% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.9","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.1","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}