{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T17:40:11Z","timestamp":1745602811134,"version":"3.40.4"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031873263","type":"print"},{"value":"9783031873270","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-87327-0_11","type":"book-chapter","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T16:07:56Z","timestamp":1745597276000},"page":"222-251","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A New Metric for\u00a0Measuring the\u00a0Intrinsic Quality in\u00a0Data Collected for\u00a0Quantitative Classification"],"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":[[2025,4,26]]},"reference":[{"key":"11_CR1","doi-asserted-by":"publisher","unstructured":"Adult: UCI machine learning repository (1996). https:\/\/doi.org\/10.24432\/C5XW20","DOI":"10.24432\/C5XW20"},{"key":"11_CR2","unstructured":"Abdelaal, M., Hammacher, C., Schoening, H.: Rein: a comprehensive benchmark framework for data cleaning methods in ml pipelines. arXiv preprint arXiv:2302.04702 (2023)"},{"key":"11_CR3","unstructured":"Askham, N., et al.: The six primary dimensions for data quality assessment. In: DAMA UK Working Group, pp. 432\u2013435 (2013)"},{"key":"11_CR4","unstructured":"Ataccama: Ataccamaone (2023). https:\/\/www.ataccama.com\/platform"},{"issue":"3","key":"11_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1541880.1541883","volume":"41","author":"C Batini","year":"2009","unstructured":"Batini, C., Cappiello, C., Francalanci, C., Maurino, A.: Methodologies for data quality assessment and improvement. ACM Comput. Surv. (CSUR) 41(3), 1\u201352 (2009)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"11_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24106-7","volume-title":"Data and Information Quality","author":"C Batini","year":"2016","unstructured":"Batini, C., Scannapieco, M., et al.: Data and Information Quality. Springer International Publishing, Cham, Switzerland (2016). https:\/\/doi.org\/10.1007\/978-3-319-24106-7"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Bors, C., Gschwandtner, T., Kriglstein, S., Miksch, S., Pohl, M.: Visual interactive creation, customization, and analysis of data quality metrics. J. Data Inf. Qual. (JDIQ) ACM 10, 1\u201326 (2018)","DOI":"10.1145\/3190578"},{"key":"11_CR8","doi-asserted-by":"publisher","first-page":"24634","DOI":"10.1109\/ACCESS.2019.2899751","volume":"7","author":"C Cichy","year":"2019","unstructured":"Cichy, C., Rass, S.: An overview of data quality frameworks. IEEE Access 7, 24634\u201324648 (2019)","journal-title":"IEEE Access"},{"key":"11_CR9","unstructured":"Cortes, C., Jackel, L.D., Chiang, W.P.: Limits on learning machine accuracy imposed by data quality. In: Advances in Neural Information Processing Systems, vol. 7 (1994)"},{"key":"11_CR10","unstructured":"DataCleaner: Datacleaner (2023). https:\/\/datacleaner.github.io\/"},{"key":"11_CR11","unstructured":"Datamartist: Datamartist (2023). http:\/\/www.datamartist.com\/"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Ehrlinger, L., W\u00f6\u00df, W.: A survey of data quality measurement and monitoring tools. Front. Big Data 5, \u00a028 (2022)","DOI":"10.3389\/fdata.2022.850611"},{"key":"11_CR13","unstructured":"Experian: User manual version 5.9 (2023). https:\/\/www.edq.com\/globalassets\/documentation\/pandora\/pandora\/manual\/590.pdf"},{"key":"11_CR14","doi-asserted-by":"publisher","unstructured":"Fisher, R.: Iris. UCI Machine Learning Repository (1988) https:\/\/doi.org\/10.24432\/C56C76","DOI":"10.24432\/C56C76"},{"key":"11_CR15","unstructured":"Foundation, A.: Apache griffin user guide (2023). https:\/\/github.com\/apache\/griffin\/blob\/master\/griffin-doc\/ui\/user-guide.md"},{"issue":"1","key":"11_CR16","first-page":"1","volume":"10","author":"V Gudivada","year":"2017","unstructured":"Gudivada, V., Apon, A., Ding, J.: Data quality considerations for big data and machine learning: going beyond data cleaning and transformations. Int. J. Adv. Softw. 10(1), 1\u201320 (2017)","journal-title":"Int. J. Adv. Softw."},{"key":"11_CR17","unstructured":"Haegmans, T., Snoeck, M., Lemahieu, W.: Towards a precise definition of data accuracy and a justification for its measure. Proceedings of the International Conference on Information Quality, p.\u00a016 (2016). mIT Information Quality (MITIQ) Program"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Hamid, M.H.A., Yusoff, M., Mohamed, A.: Survey on highly imbalanced multi-class data. Int. J. Adv. Comput. Sci. Appl. 13(2) (2022)","DOI":"10.14569\/IJACSA.2022.0130627"},{"key":"11_CR19","unstructured":"Heinrich, B., Klier, M.: A novel data quality metric for timeliness considering supplemental data. In: Information Systems in a Globalising World : Challenges, Ethics and Practices; 17th European Conference on Information Systems, pp. 2701\u20132713 (2009)"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Hinrichs, H.: Datenqualit\u00e4tsmanagement in data warehouse-systemen. Ph.D. thesis, Universit\u00e4t Oldenburg (2002)","DOI":"10.1007\/978-3-642-56687-5_15"},{"key":"11_CR21","unstructured":"IBM: IBM data quality for AI API (2023). https:\/\/developer.ibm.com\/apis\/catalog\/dataquality4ai--data-quality-for-ai\/Introduction"},{"key":"11_CR22","unstructured":"Informatica: What is data quality? (2023). https:\/\/www.informatica.com\/resources\/articles\/what-is-data-quality.html"},{"key":"11_CR23","unstructured":"InfoZoom: Infozoom & IZDQ (2023). https:\/\/www.infozoom.com\/en\/products\/infozoom-data-quality\/"},{"key":"11_CR24","doi-asserted-by":"publisher","unstructured":"Jouseau, R., Salva, S., Samir, C.: On Studying the\u00a0Effect of\u00a0Data Quality on\u00a0Classification Performances. In: Intelligent Data Engineering and Automated Learning - IDEAL 2022. Lecture Notes in Computer Science, vol. 13756, pp. 82\u201393. Springer International Publishing, Manchester, United Kingdom (2022). https:\/\/doi.org\/10.1007\/978-3-031-21753-1_9, https:\/\/hal.uca.fr\/hal-03938077","DOI":"10.1007\/978-3-031-21753-1_9"},{"key":"11_CR25","unstructured":"Jouseau, R., Salva, S., Samir, C.: Additional resources for the reproducibility of the experiment (2023). https:\/\/gitlab.com\/roxane.jouseau\/measuring-data-quality-for-classification-tasks"},{"key":"11_CR26","doi-asserted-by":"publisher","unstructured":"Jouseau, R., Salva, S., Samir, C.: A novel metric for measuring data quality in classification applications. In: Rocha, A.P., Steels, L., van\u00a0den Herik, H.J. (eds.) Proceedings of the 16th International Conference on Agents and Artificial Intelligence, ICAART 2024, Volume 3, Rome, Italy, 24-26 February 2024, pp. 141\u2013148. SCITEPRESS (2024). https:\/\/doi.org\/10.5220\/0012311500003636","DOI":"10.5220\/0012311500003636"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Lettner, C., Stumptner, R., Fragner, W., Rauchenzauner, F., Ehrlinger, L.: DAQL 2.0: measure data quality based on entity models. Procedia Comput. Sci. 180, 772\u2013777 (2021)","DOI":"10.1016\/j.procs.2021.01.327"},{"key":"11_CR28","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":"11_CR29","doi-asserted-by":"crossref","unstructured":"Ma, L., et al.: DeepMutation: mutation testing of deep learning systems. arXiv:1805.05206 (2018)","DOI":"10.1109\/ISSRE.2018.00021"},{"key":"11_CR30","unstructured":"Kelly, M., Rachel\u00a0Longjohn, K.N.: The UCI machine learning repository. https:\/\/archive.ics.uci.edu"},{"key":"11_CR31","unstructured":"Moore, S.: How to create a business case for data quality improvement. Gartner Research (2018)"},{"issue":"2","key":"11_CR32","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/s13222-022-00413-2","volume":"22","author":"F Neutatz","year":"2022","unstructured":"Neutatz, F., Chen, B., Alkhatib, Y., Ye, J., Abedjan, Z.: Data cleaning and AutoML: would an optimizer choose to clean? Datenbank-Spektrum 22(2), 121\u2013130 (2022). https:\/\/doi.org\/10.1007\/s13222-022-00413-2","journal-title":"Datenbank-Spektrum"},{"key":"11_CR33","unstructured":"OpenRefine: OpenRefine (2023). https:\/\/github.com\/OpenRefine\/OpenRefine"},{"key":"11_CR34","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":"4","key":"11_CR35","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1145\/505248.506010","volume":"45","author":"LL Pipino","year":"2002","unstructured":"Pipino, L.L., Lee, Y.W., Wang, R.Y.: Data quality assessment. Commun. ACM 45(4), 211\u2013218 (2002)","journal-title":"Commun. ACM"},{"key":"11_CR36","doi-asserted-by":"publisher","unstructured":"Ridzuan, F., Wan Zainon, W.M.N.: A review on data cleansing methods for big data. Procedia Comput. Sci. 161, 731\u2013738 (2019). https:\/\/doi.org\/10.1016\/j.procs.2019.11.177, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050919318885, the Fifth Information Systems International Conference, 23-24 July 2019, Surabaya, Indonesia","DOI":"10.1016\/j.procs.2019.11.177"},{"key":"11_CR37","unstructured":"Rolland, A.: MobyDQ (2023). https:\/\/ubisoft.github.io\/mobydq"},{"key":"11_CR38","unstructured":"SAS: DataFlux data management studio 2.7: User guide (2023). http:\/\/support.sas.com\/documentation\/onlinedoc\/dfdmstudio\/2.7\/dmpdmsug\/dfUnity.html"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Sebastian-Coleman, L.: Measuring data quality for ongoing improvement: a data quality assessment framework. Newnes (2012)","DOI":"10.1016\/B978-0-12-397033-6.00020-1"},{"key":"11_CR40","unstructured":"Sherin, S., Iqbal, M.Z., et\u00a0al.: A systematic mapping study on testing of machine learning programs. arXiv preprint arXiv:1907.09427 (2019)"},{"key":"11_CR41","unstructured":"Talend: Talend open studio for data quality - user guide 7.0.1m2 (2023). http:\/\/download-mirror1.talend.com\/top\/user-guide-download\/V552\/TalendOpenStudio_DQ_UG_5.5.2_EN.pdf"},{"issue":"4","key":"11_CR42","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1080\/07421222.1996.11518099","volume":"12","author":"RY Wang","year":"1996","unstructured":"Wang, R.Y., Strong, D.M.: Beyond accuracy: What data quality means to data consumers. J. Manag. Inf. Syst. 12(4), 5\u201333 (1996)","journal-title":"J. Manag. Inf. Syst."},{"key":"11_CR43","doi-asserted-by":"publisher","unstructured":"Wolberg, W., Mangasarian, O., Street, N., Street, W.: Breast cancer wisconsin (diagnostic). UCI machine learning repository (1995). https:\/\/doi.org\/10.24432\/C5DW2B","DOI":"10.24432\/C5DW2B"}],"container-title":["Lecture Notes in Computer Science","Agents and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-87327-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T17:02:25Z","timestamp":1745600545000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-87327-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031873263","9783031873270"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-87327-0_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICAART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Agents and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 February 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icaart2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icaart.scitevents.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}