{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:47:42Z","timestamp":1743029262905,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031429132"},{"type":"electronic","value":"9783031429149"}],"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\/978-3-031-42914-9_14","type":"book-chapter","created":{"date-parts":[[2023,8,27]],"date-time":"2023-08-27T23:02:26Z","timestamp":1693177346000},"page":"195-209","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Assessment of\u00a0Data Quality Through Multi-granularity Data Profiling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8143-7615","authenticated-orcid":false,"given":"Claudia","family":"Diamantini","sequence":"first","affiliation":[]},{"given":"Alessandro","family":"Mele","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7067-5463","authenticated-orcid":false,"given":"Domenico","family":"Potena","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5966-6921","authenticated-orcid":false,"given":"Emanuele","family":"Storti","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,28]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Jarke, M., Jeusfeld, M.A., Quix, C., Vassiliadis, P.: Architecture and quality in data warehouses: an extended repository approach. Inf. Syst. 24(3), 229\u2013253 (1999). 10th International Conference on Advanced Information Systems Engineering","DOI":"10.1016\/S0306-4379(99)00017-4"},{"key":"14_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, 557\u2013581 (2015)","journal-title":"VLDB J."},{"issue":"3","key":"14_CR3","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":"14_CR4","doi-asserted-by":"crossref","unstructured":"Brickley, D., Burgess, M., Noy, N.: Google dataset search: building a search engine for datasets in an open web ecosystem. In: The World Wide Web Conference, pp. 1365\u20131375 (2019)","DOI":"10.1145\/3308558.3313685"},{"key":"14_CR5","unstructured":"Broder, A.Z.: On the resemblance and containment of documents. In: Proceedings of the Compression and Complexity of SEQUENCES 1997 (Cat. No. 97TB100171), pp. 21\u201329. IEEE (1997)"},{"key":"14_CR6","unstructured":"World Wide Web Consortium, et al.: The RDF data cube vocabulary. Technical report, World Wide Web Consortium (2014)"},{"key":"14_CR7","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s10796-020-10010-x","volume":"23","author":"C Diamantini","year":"2021","unstructured":"Diamantini, C., Lo Giudice, P., Potena, D., Storti, E., Ursino, D.: An approach to extracting topic-guided views from the sources of a data lake. Inf. Syst. Front. 23, 243\u2013262 (2021)","journal-title":"Inf. Syst. Front."},{"key":"14_CR8","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1016\/j.future.2015.04.011","volume":"54","author":"C Diamantini","year":"2016","unstructured":"Diamantini, C., Potena, D., Storti, E.: SemPI: a semantic framework for the collaborative construction and maintenance of a shared dictionary of performance indicators. Fut. Gen. Comput. Syst. 54, 352\u2013365 (2016)","journal-title":"Fut. Gen. Comput. Syst."},{"key":"14_CR9","doi-asserted-by":"publisher","unstructured":"Diamantini, C., Potena, D., Storti, E.: A knowledge-based approach to support analytic query answering in semantic data lakes. In: Chiusano, S., Cerquitelli, T., Wrembel, R. (eds.) Advances in Databases and Information Systems, ADBIS 2022. LNCS, vol. 13389. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15740-0_14","DOI":"10.1007\/978-3-031-15740-0_14"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Farid, M., Roatis, A., Ilyas, I.F., Hoffmann, H., Chu, X.: CLAMS: bringing quality to Data Lakes. In: Proceedings of the International Conference on Management of Data (SIGMOD\/PODS 2016), San Francisco, CA, USA, pp. 2089\u20132092. ACM (2016)","DOI":"10.1145\/2882903.2899391"},{"key":"14_CR11","unstructured":"Friedman, T., Smith, M.: Measuring the business value of data quality. Technical report, Gartner (2011)"},{"issue":"3","key":"14_CR12","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1145\/581751.581753","volume":"27","author":"PB Gibbons","year":"2002","unstructured":"Gibbons, P.B., Matias, Y., Poosala, V.: Fast incremental maintenance of approximate histograms. ACM Trans. Database Syst. (TODS) 27(3), 261\u2013298 (2002)","journal-title":"ACM Trans. Database Syst. (TODS)"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Hai, R., Geisler, S., Quix, C.: Constance: an intelligent data lake system. In: Proceedings of the International Conference on Management of Data, SIGMOD 2016, San Francisco, CA, USA, pp. 2097\u20132100. ACM (2016)","DOI":"10.1145\/2882903.2899389"},{"key":"14_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/978-3-030-33223-5_19","volume-title":"Conceptual Modeling","author":"R Hai","year":"2019","unstructured":"Hai, R., Quix, C., Wang, D.: Relaxed functional dependency discovery in heterogeneous data lakes. In: Laender, A.H.F., Pernici, B., Lim, E.-P., de Oliveira, J.P.M. (eds.) ER 2019. LNCS, vol. 11788, pp. 225\u2013239. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-33223-5_19"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Hulsebos, M., et al.: Sherlock: a deep learning approach to semantic data type detection. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1500\u20131508 (2019)","DOI":"10.1145\/3292500.3330993"},{"issue":"2","key":"14_CR16","doi-asserted-by":"publisher","first-page":"85","DOI":"10.26599\/BDMA.2019.9020015","volume":"3","author":"MS Mahmud","year":"2020","unstructured":"Mahmud, M.S., Huang, J.Z., Salloum, S., Emara, T.Z., Sadatdiynov, K.: A survey of data partitioning and sampling methods to support big data analysis. Big Data Min. Anal. 3(2), 85\u2013101 (2020)","journal-title":"Big Data Min. Anal."},{"key":"14_CR17","volume-title":"Managing the Data Lake","author":"A Oram","year":"2015","unstructured":"Oram, A.: Managing the Data Lake. O\u2019Reilly, Sebastopol (2015)"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Song, J., He, Y.: Auto-validate: unsupervised data validation using data-domain patterns inferred from data lakes. In: Proceedings of the 2021 International Conference on Management of Data, pp. 1678\u20131691 (2021)","DOI":"10.1145\/3448016.3457250"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, D., Suhara, Y., Li, J., Hulsebos, M., Demiralp, \u00c7., Tan, W.-C.: Sato: contextual semantic type detection in tables. arXiv preprint arXiv:1911.06311 (2019)","DOI":"10.14778\/3407790.3407793"},{"issue":"12","key":"14_CR20","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.14778\/2994509.2994534","volume":"9","author":"E Zhu","year":"2016","unstructured":"Zhu, E., Nargesian, F., Pu, K.Q., Miller, R.J.: LSH ensemble: Internet-scale domain search. Proc. VLDB Endow. 9(12), 1185\u20131196 (2016)","journal-title":"Proc. VLDB Endow."},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Zouari, F., Kabachi, N., Boukadi, K., Guegan, C.G.: Data management in the data lake: a systematic mapping. In: Proceedings of the 25th International Database Engineering & Applications Symposium, pp. 280\u2013284 (2021)","DOI":"10.1145\/3472163.3472173"}],"container-title":["Lecture Notes in Computer Science","Advances in Databases and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-42914-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,27]],"date-time":"2023-08-27T23:16:21Z","timestamp":1693178181000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-42914-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031429132","9783031429149"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-42914-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"28 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADBIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Advances in Databases and Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Barcelona","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adbis2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/adbis.eu\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"77","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":"14","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":"25","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":"18% - 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":"N\/A","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":"N\/A","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}