{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:06:21Z","timestamp":1776679581193,"version":"3.51.2"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031378898","type":"print"},{"value":"9783031378904","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-37890-4_2","type":"book-chapter","created":{"date-parts":[[2023,7,22]],"date-time":"2023-07-22T21:01:44Z","timestamp":1690059704000},"page":"24-44","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Automating Data Quality Monitoring with\u00a0Reference Data Profiles"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5313-0368","authenticated-orcid":false,"given":"Lisa","family":"Ehrlinger","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7830-3138","authenticated-orcid":false,"given":"Bernhard","family":"Werth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfram","family":"W\u00f6\u00df","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,23]]},"reference":[{"issue":"4","key":"2_CR1","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1145\/3385658.3385668","volume":"48","author":"D Abadi","year":"2019","unstructured":"Abadi, D., et al.: The Seattle report on database research. ACM SIGMOD Rec. 48(4), 44\u201353 (2019)","journal-title":"ACM SIGMOD Rec."},{"issue":"4","key":"2_CR2","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/s00778-015-0389-y","volume":"24","author":"Z Abedjan","year":"2015","unstructured":"Abedjan, Z., Golab, L., Naumann, F.: Profiling relational data: a survey. VLDB J. 24(4), 557\u2013581 (2015)","journal-title":"VLDB J."},{"issue":"4","key":"2_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-01865-7","volume":"10","author":"Z Abedjan","year":"2019","unstructured":"Abedjan, Z., Golab, L., Naumann, F., Papenbrock, T.: Data profiling. Synth. Lect. Data Manag. 10(4), 1\u2013154 (2019)","journal-title":"Synth. Lect. Data Manag."},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Breunig, M.M., Kriegel, H.P., Ng, R.T., Sander, J.: LOF: identifying density-based local outliers. In: Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, pp. 93\u2013104 (2000)","DOI":"10.1145\/342009.335388"},{"key":"2_CR5","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/978-3-030-86967-0_10","volume-title":"Flexible Query Answering Systems","author":"A Bronselaer","year":"2021","unstructured":"Bronselaer, A.: Data quality management: an overview of methods and challenges. In: Andreasen, T., De Tr\u00e9, G., Kacprzyk, J., Legind Larsen, H., Bordogna, G., Zadro\u017cny, S. (eds.) FQAS 2021. LNCS (LNAI), vol. 12871, pp. 127\u2013141. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86967-0_10"},{"issue":"2","key":"2_CR6","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1109\/TFUZZ.2017.2686807","volume":"26","author":"A Bronselaer","year":"2018","unstructured":"Bronselaer, A., De Mol, R., De Tr\u00e9, G.: A measure-theoretic foundation for data quality. IEEE Trans. Fuzzy Syst. 26(2), 627\u2013639 (2018)","journal-title":"IEEE Trans. Fuzzy Syst."},{"issue":"1\u20132","key":"2_CR7","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3233\/DS-170006","volume":"1","author":"D Dell\u2019Aglio","year":"2017","unstructured":"Dell\u2019Aglio, D., Della Valle, E., van Harmelen, F., Bernstein, A.: Stream reasoning: a survey and outlook. Data Sci. 1(1\u20132), 59\u201383 (2017)","journal-title":"Data Sci."},{"issue":"5","key":"2_CR8","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1016\/S1473-3099(20)30120-1","volume":"20","author":"E Dong","year":"2020","unstructured":"Dong, E., Du, H., Gardner, L.: An interactive web-based dashboard to track COVID-19 in real time. Lancet. Infect. Dis 20(5), 533\u2013534 (2020)","journal-title":"Lancet. Infect. Dis"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Ehrlinger, L., Gindlhumer, A., Huber, L., W\u00f6\u00df, W.: DQ-MeeRKat: automating data quality monitoring with a reference-data-profile-annotated knowledge graph. In: Proceedings of the 10th International Conference on Data Science, Technology and Applications - DATA, pp. 215\u2013222. SciTePress (2021)","DOI":"10.5220\/0010546200002993"},{"issue":"3 & 4","key":"2_CR10","first-page":"400","volume":"11","author":"L Ehrlinger","year":"2018","unstructured":"Ehrlinger, L., Werth, B., W\u00f6\u00df, W.: Automated continuous data quality measurement with QuaIIe. Int. J. Adv. Softw. 11(3 & 4), 400\u2013417 (2018)","journal-title":"Int. J. Adv. Softw."},{"key":"2_CR11","unstructured":"Ehrlinger, L., W\u00f6\u00df, W.: Semi-automatically generated hybrid ontologies for information integration. In: SEMANTiCS (Posters & Demos). CEUR Workshop Proceedings, vol.\u00a01481, pp. 100\u2013104. RWTH, Aachen (2015)"},{"key":"2_CR12","unstructured":"Ehrlinger, L., W\u00f6\u00df, W.: Towards a definition of knowledge graphs. In: Martin, M., Cuquet, M., Folmer, E. (eds.) Joint Proceedings of the Posters and Demos Track of 12th International Conference on Semantic Systems - SEMANTiCS2016 and 1st International Workshop on Semantic Change & Evolving Semantics (SuCCESS16). CEUR Workshop Proceedings, vol. 1695, pp. 13\u201316. Technical University of Aachen (RWTH), Aachen, Germany (2016)"},{"key":"2_CR13","unstructured":"Ehrlinger, L., W\u00f6\u00df, W.: Automated data quality monitoring. In: Talburt, J.R. (ed.) Proceedings of the 22nd MIT International Conference on Information Quality (MIT ICIQ), UA Little Rock, Arkansas, USA, pp. 15.1\u201315.9 (2017)"},{"key":"2_CR14","doi-asserted-by":"publisher","unstructured":"Ehrlinger, L., W\u00f6\u00df, W.: A survey of data quality measurement and monitoring tools. Front. Big Data 5(850611) (2022). https:\/\/doi.org\/10.3389\/fdata.2022.850611","DOI":"10.3389\/fdata.2022.850611"},{"issue":"1","key":"2_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","volume":"19","author":"AK Elmagarmid","year":"2007","unstructured":"Elmagarmid, A.K., Ipeirotis, P.G., Verykios, V.S.: Duplicate record detection: a survey. IEEE Trans. Knowl. Data Eng. 19(1), 1\u201316 (2007)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37439-6","volume-title":"Knowledge Graphs","author":"D Fensel","year":"2020","unstructured":"Fensel, D., et al.: Knowledge Graphs. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-37439-6"},{"issue":"1","key":"2_CR17","doi-asserted-by":"publisher","first-page":"56","DOI":"10.3390\/make3010004","volume":"3","author":"L Fischer","year":"2021","unstructured":"Fischer, L., et al.: AI system engineering-key challenges and lessons learned. Mach. Learn. Knowl. Extr. 3(1), 56\u201383 (2021)","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"2_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-030-27520-4_13","volume-title":"Big Data Analytics and Knowledge Discovery","author":"C Giebler","year":"2019","unstructured":"Giebler, C., Gr\u00f6ger, C., Hoos, E., Schwarz, H., Mitschang, B.: Leveraging the data lake: current state and challenges. In: Ordonez, C., Song, I.-Y., Anderst-Kotsis, G., Tjoa, A.M., Khalil, I. (eds.) DaWaK 2019. LNCS, vol. 11708, pp. 179\u2013188. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-27520-4_13"},{"key":"2_CR19","unstructured":"Haegemans, T., Snoeck, M., Lemahieu, W.: Towards a precise definition of data accuracy and a justification for its measure. In: Proceedings of the International Conference on Information Quality (ICIQ 2016), Ciudad Real, Spain, pp. 16.1\u201316.13. Alarcos Research Group (UCLM) (2016)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Heidari, A., McGrath, J., Ilyas, I.F., Rekatsinas, T.: Holodetect: few-shot learning for error detection. In: International Conference on Management of Data (SIGMOD 2019), New York, NY, USA, pp. 829\u2013846. ACM (2019)","DOI":"10.1145\/3299869.3319888"},{"key":"2_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1007\/978-3-030-27615-7_18","volume-title":"Database and Expert Systems Applications","author":"F Heine","year":"2019","unstructured":"Heine, F., Kleiner, C., Oelsner, T.: Automated detection and monitoring of advanced data quality rules. In: Hartmann, S., K\u00fcng, J., Chakravarthy, S., Anderst-Kotsis, G., Tjoa, A.M., Khalil, I. (eds.) DEXA 2019. LNCS, vol. 11706, pp. 238\u2013247. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-27615-7_18"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Heinrich, B., Hristova, D., Klier, M., Schiller, A., Szubartowicz, M.: Requirements for data quality metrics. J. Data Inf. Qual. 9(2), 12:1\u201312:32 (2018)","DOI":"10.1145\/3148238"},{"key":"2_CR23","unstructured":"Hogan, A., et al.: Knowledge Graphs. CoRR (2020). https:\/\/arxiv.org\/abs\/2003.02320"},{"key":"2_CR24","unstructured":"Kaiser, M., Klier, M., Heinrich, B.: How to measure data quality? - a metric-based approach. In: International Conference on Information Systems, Montreal, Canada, pp. 1\u201315. AIS Electronic Library (AISeL) (2007)"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Kandel, S., Paepcke, A., Hellerstein, J., Heer, J.: Wrangler: interactive visual specification of data transformation scripts. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Vancouver, BC, Canada. ACM (2011)","DOI":"10.1145\/1978942.1979444"},{"key":"2_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1007\/11581116_19","volume-title":"Web Information Systems Engineering \u2013 WISE 2005 Workshops","author":"A Kiryakov","year":"2005","unstructured":"Kiryakov, A., Ognyanov, D., Manov, D.: OWLIM \u2013 a pragmatic semantic repository for OWL. In: Dean, M., et al. (eds.) WISE 2005. LNCS, vol. 3807, pp. 182\u2013192. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11581116_19"},{"issue":"2","key":"2_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1577840.1577845","volume":"1","author":"A Klein","year":"2009","unstructured":"Klein, A., Lehner, W.: Representing data quality in sensor data streaming environments. J. Data Inf. Qual. (JDIQ) 1(2), 1\u201328 (2009)","journal-title":"J. Data Inf. Qual. (JDIQ)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Laranjeiro, N., Soydemir, S.N., Bernardino, J.: A survey on data quality: classifying poor data. In: Proceedings of the 21st Pacific Rim International Symposium on Dependable Computing (PRDC), Zhangjiajie, China, pp. 179\u2013188. IEEE (2015)","DOI":"10.1109\/PRDC.2015.41"},{"key":"2_CR29","unstructured":"Ledvinka, M., K\u0159emen, P.: A comparison of object-triple mapping libraries. Semant. Web 1\u201343 (2019)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation forest. In: 2008 Eighth IEEE International Conference on Data Mining, pp. 413\u2013422. IEEE (2008)","DOI":"10.1109\/ICDM.2008.17"},{"key":"2_CR31","unstructured":"Naqvi, S.N.Z., Yfantidou, S., Zim\u00e1nyi, E.: Time Series Databases and InfluxDB. Technical report, Universit\u00e9 Libre de Bruxelles (2017)"},{"key":"2_CR32","first-page":"37","volume":"1","author":"L Pipino","year":"2005","unstructured":"Pipino, L., Wang, R., Kopcso, D., Rybolt, W.: Developing measurement scales for data-quality dimensions. Inf. Qual. 1, 37\u201352 (2005)","journal-title":"Inf. Qual."},{"key":"2_CR33","unstructured":"Redyuk, S., Kaoudi, Z., Markl, V., Schelter, S.: Automating data quality validation for dynamic data ingestion. In: Proceedings of the 24th International Conference on Extending Database Technology (EDBT) (2021)"},{"key":"2_CR34","first-page":"1","volume":"2","author":"M Scannapieco","year":"2002","unstructured":"Scannapieco, M., Catarci, T.: Data quality under a computer science perspective. Archivi Comput. 2, 1\u201315 (2002)","journal-title":"Archivi Comput."},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Sebastian-Coleman, L.: Measuring Data Quality for Ongoing Improvement: A Data Quality Assessment Framework. Elsevier, Waltham, MA, USA (2013)","DOI":"10.1016\/B978-0-12-397033-6.00020-1"},{"key":"2_CR36","unstructured":"Stonebraker, M., et al.: Data curation at scale: the data tamer system. In: 6th Biennial Conference on Innovative Data Systems Research (CDIR 2013), Asilomar, California, USA (2013)"},{"key":"2_CR37","unstructured":"Stonebraker, M., Ilyas, I.F.: Data integration: the current status and the way forward. Bull. IEEE Comput. Soc. Tech. Committee Data Eng. 41(2), 3\u20139 (2018)"},{"issue":"153","key":"2_CR38","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1080\/01621459.1926.10502161","volume":"21","author":"HA Sturges","year":"1926","unstructured":"Sturges, H.A.: The choice of a class interval. J. Am. Stat. Assoc. 21(153), 65\u201366 (1926)","journal-title":"J. Am. Stat. Assoc."},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Talburt, J.R., Al Sarkhi, A.K., Pullen, D., Claassens, L., Wang, R.: An iterative, self-assessing entity resolution system: first steps toward a data washing machine. Int. J. Adv. Comput. Sci. Appl. 11(12) (2020)","DOI":"10.14569\/IJACSA.2020.0111279"},{"issue":"4","key":"2_CR40","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.: 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":"2_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2019.106031","volume":"137","author":"J Zenisek","year":"2019","unstructured":"Zenisek, J., Holzinger, F., Affenzeller, M.: Machine learning based concept drift detection for predictive maintenance. Comput. Ind. Eng. 137, 106031 (2019)","journal-title":"Comput. Ind. Eng."}],"container-title":["Communications in Computer and Information Science","Data Management Technologies and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-37890-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,22]],"date-time":"2023-07-22T21:02:15Z","timestamp":1690059735000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-37890-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031378898","9783031378904"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-37890-4_2","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"23 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DATA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Data Management Technologies and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 July 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 July 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"data2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/dataconference.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"PRIMORIS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"84","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":"17","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":"22","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":"20% - 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":"3","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":"4","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)"}}]}}