{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:31:28Z","timestamp":1743103888252,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030195038"},{"type":"electronic","value":"9783030195045"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-19504-5_15","type":"book-chapter","created":{"date-parts":[[2019,5,14]],"date-time":"2019-05-14T04:38:43Z","timestamp":1557808723000},"page":"221-236","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Anomaly-Based Duplicate Detection: A Probabilistic Approach"],"prefix":"10.1007","author":[{"given":"Andreas","family":"Obermeier","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,4,27]]},"reference":[{"issue":"3","key":"15_CR1","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1145\/2854006.2854008","volume":"44","author":"W Fan","year":"2015","unstructured":"Fan, W.: Data quality. From theory to practice. ACM SIGMOD Rec. 44(3), 7\u201318 (2015). https:\/\/doi.org\/10.1145\/2854006.2854008","journal-title":"ACM SIGMOD Rec."},{"key":"15_CR2","unstructured":"Helmis, S., Hollmann, R.: Webbased Dataintegration. Approaches to Measure and Maintain the Quality of Information in Heterogeneous Databases Using a Fully Web-Based Tool. Springer, Heidelberg (2009)"},{"key":"15_CR3","unstructured":"Heinrich, B., Klier, M., Obermeier, A.A., Schiller, A.: Event-driven duplicate detection: a probability-based approach. In: Proceedings of the 26th ECIS (2018)"},{"key":"15_CR4","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-658-09214-6_7","volume-title":"Daten- und Informationsqualit\u00e4t","author":"Jens Bleiholder","year":"2015","unstructured":"Bleiholder, J., Schmid, J.: Dataintegration and deduplication. In: Daten- und Informationsqualit\u00e4t, pp. 121\u2013140. Springer, Heidelberg (2015)"},{"key":"15_CR5","volume-title":"Partitioning for Efficient Duplicate Detection in Relational Data","author":"U Draisbach","year":"2012","unstructured":"Draisbach, U.: Partitioning for Efficient Duplicate Detection in Relational Data. Springer, Heidelberg (2012)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Christen, P.: Automatic record linkage using seeded nearest neighbour and support vector machine classification. In: Proceedings of the 14th ACM SIGKDD, pp. 151\u2013159 (2008)","DOI":"10.1145\/1401890.1401913"},{"key":"15_CR7","unstructured":"Christen, P.: A two-step classification approach to unsupervised record linkage. In: Proceedings of the 6th AusDM, pp. 111\u2013119 (2007)"},{"key":"15_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/11890591_5","volume-title":"Journal on Data Semantics VII","author":"P Lehti","year":"2006","unstructured":"Lehti, P., Fankhauser, P.: Unsupervised duplicate detection using sample non-duplicates. In: Spaccapietra, S. (ed.) Journal on Data Semantics VII. LNCS, vol. 4244, pp. 136\u2013164. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11890591_5"},{"key":"15_CR9","unstructured":"Elfeky, M.G., Verykios, V.S., Elmagarmid, A.K.: TAILOR: a record linkage toolbox. In: Proceedings of the 18th ICDE, pp. 17\u201328 (2002)"},{"key":"15_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/11677437_12","volume-title":"Data Mining","author":"L Gu","year":"2006","unstructured":"Gu, L., Baxter, R.: Decision models for record linkage. In: Williams, G.J., Simoff, S.J. (eds.) Data Mining. LNCS (LNAI), vol. 3755, pp. 146\u2013160. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11677437_12"},{"key":"15_CR11","unstructured":"Ravikumar, P., Cohen, W.W.: A hierarchical graphical model for record linkage. In: Proceedings of the 20th UAI, pp. 454\u2013461 (2004)"},{"key":"15_CR12","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-319-93040-4_15","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"A Jurek","year":"2018","unstructured":"Jurek, A., Deepak, P.: It pays to be certain: unsupervised record linkage via ambiguity minimization. In: Phung, D., Tseng, V.S., Webb, G.I., Ho, B., Ganji, M., Rashidi, L. (eds.) PAKDD 2018. LNCS (LNAI), vol. 10939, pp. 177\u2013190. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-93040-4_15"},{"issue":"3","key":"15_CR13","first-page":"45","volume":"24","author":"K Peffers","year":"2007","unstructured":"Peffers, K., Tuunanen, T., Rothenberger, M.A., Chatterjee, S.: A design science research methodology for information systems research. JMIS 24(3), 45\u201377 (2007)","journal-title":"JMIS"},{"key":"15_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31164-2","volume-title":"Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection","author":"P Christen","year":"2012","unstructured":"Christen, P.: Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31164-2"},{"issue":"1","key":"15_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":"15_CR16","doi-asserted-by":"crossref","unstructured":"Winkler, W.E.: Overview of record linkage and current research directions. U.S. Bureau of the Census (2006)","DOI":"10.1002\/9780470057339.var022"},{"issue":"5","key":"15_CR17","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1016\/j.jclinepi.2010.05.008","volume":"64","author":"M Tromp","year":"2011","unstructured":"Tromp, M., Ravelli, A.C., Bonsel, G.J., Hasman, A., Reitsma, J.B.: Results from simulated data sets. Probabilistic record linkage outperforms deterministic record linkage. J. Clin. Epidemiol. 64(5), 565\u2013572 (2011)","journal-title":"J. Clin. Epidemiol."},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Hettiarachchi, G.P., Hettiarachchi, N.N., Hettiarachchi, D.S., Ebisuya, A.: Next generation data classification and linkage. Role of probabilistic models and artificial intelligence. In: Proceedings of the 4th IEEE GHTC, pp. 569\u2013576 (2014)","DOI":"10.1109\/GHTC.2014.6970340"},{"issue":"328","key":"15_CR19","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","volume":"64","author":"IP Fellegi","year":"1969","unstructured":"Fellegi, I.P., Sunter, A.B.: A theory for record linkage. J. Am. Stat. Assoc. 64(328), 1183\u20131210 (1969)","journal-title":"J. Am. Stat. Assoc."},{"issue":"430","key":"15_CR20","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1080\/01621459.1995.10476563","volume":"90","author":"TR Belin","year":"1995","unstructured":"Belin, T.R., Rubin, D.B.: A method for calibrating false-match rates in record linkage. J. Am. Stat. Assoc. 90(430), 694\u2013707 (1995)","journal-title":"J. Am. Stat. Assoc."},{"issue":"516","key":"15_CR21","doi-asserted-by":"publisher","first-page":"1660","DOI":"10.1080\/01621459.2015.1105807","volume":"111","author":"RC Steorts","year":"2016","unstructured":"Steorts, R.C., Hall, R., Fienberg, S.E.: A Bayesian approach to graphical record linkage and deduplication. J. Am. Stat. Assoc. 111(516), 1660\u20131672 (2016)","journal-title":"J. Am. Stat. Assoc."},{"key":"15_CR22","unstructured":"Thibaudeau, Y.: The discrimination power of dependency structures in record linkage. U.S. Bureau of the Census (1992)"},{"key":"15_CR23","unstructured":"Winkler, W.E.: Improved decision rules in the Fellegi-Sunter model of record linkage. In: Proceedings of Survey Research Methods Section, pp. 274\u2013279. American Statistical Association (1993)"},{"key":"15_CR24","doi-asserted-by":"publisher","DOI":"10.1002\/9781118575574","volume-title":"Multivariate Density Estimation. Theory, Practice, and Visualization","author":"DW Scott","year":"2015","unstructured":"Scott, D.W.: Multivariate Density Estimation. Theory, Practice, and Visualization. Wiley, Hoboken (2015)"},{"key":"15_CR25","unstructured":"Cohen, W., Ravikumar, P., Fienberg, S.: A comparison of string metrics for matching names and records. In: KDD Workshop on Data Cleaning, pp. 73\u201378 (2003)"},{"key":"15_CR26","unstructured":"Winkler, W.E.: String comparator metrics and enhanced decision rules in the Fellegi-Sunter model of record linkage. U.S. Bureau of the Census (1990)"},{"issue":"8","key":"15_CR27","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions, and reversals. Sov. Phys. Dokl. 10(8), 707\u2013710 (1966)","journal-title":"Sov. Phys. Dokl."},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Seabold, S., Perktold, J.: Statsmodels. Econometric and statistical modeling with python. In: Proceedings of the 9th Python in Science Conference, pp. 57\u201361 (2010)","DOI":"10.25080\/Majora-92bf1922-011"},{"issue":"2","key":"15_CR29","doi-asserted-by":"publisher","first-page":"227","DOI":"10.2307\/2344550","volume":"137","author":"AE Hoerl","year":"1974","unstructured":"Hoerl, A.E., Fallin, H.K.: Reliability of subjective evaluations in a high incentive situation. J. Roy. Stat. Soc. Ser. A (General) 137(2), 227\u2013230 (1974)","journal-title":"J. Roy. Stat. Soc. Ser. A (General)"},{"issue":"1","key":"15_CR30","doi-asserted-by":"publisher","first-page":"41","DOI":"10.2307\/2346866","volume":"26","author":"AH Murphy","year":"1977","unstructured":"Murphy, A.H., Winkler, R.L.: Reliability of subjective probability forecasts of precipitation and temperature. Appl. Stat. 26(1), 41\u201347 (1977)","journal-title":"Appl. Stat."},{"issue":"7","key":"15_CR31","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1175\/1520-0493(1987)115<1330:AGFFFV>2.0.CO;2","volume":"115","author":"AH Murphy","year":"1987","unstructured":"Murphy, A.H., Winkler, R.L.: A general framework for forecast verification. Mon. Weather Rev. 115(7), 1330\u20131338 (1987)","journal-title":"Mon. Weather Rev."},{"issue":"2","key":"15_CR32","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1175\/1520-0450(1963)002<0191:OSPF>2.0.CO;2","volume":"2","author":"F Sanders","year":"1963","unstructured":"Sanders, F.: On subjective probability forecasting. J. Appl. Meteorol. 2(2), 191\u2013201 (1963)","journal-title":"J. Appl. Meteorol."},{"issue":"3","key":"15_CR33","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1175\/WAF993.1","volume":"22","author":"J Br\u00f6cker","year":"2007","unstructured":"Br\u00f6cker, J., Smith, L.A.: Increasing the reliability of reliability diagrams. Weather Forecast. 22(3), 651\u2013661 (2007)","journal-title":"Weather Forecast."},{"issue":"4","key":"15_CR34","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1175\/1520-0450(1973)012<0595:ANVPOT>2.0.CO;2","volume":"12","author":"AH Murphy","year":"1973","unstructured":"Murphy, A.H.: A new vector partition of the probability score. J. Appl. Meteorol. 12(4), 595\u2013600 (1973)","journal-title":"J. Appl. Meteorol."},{"issue":"1","key":"15_CR35","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1148\/radiology.143.1.7063747","volume":"143","author":"JA Hanley","year":"1982","unstructured":"Hanley, J.A., McNeil, B.J.: The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1), 29\u201336 (1982)","journal-title":"Radiology"},{"key":"15_CR36","unstructured":"de Bruin, J.: Python Record Linkage Toolkit. https:\/\/github.com\/J535D165\/recordlinkage . Accessed 4 Jan 2019"}],"container-title":["Lecture Notes in Computer Science","Extending the Boundaries of Design Science Theory and Practice"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-19504-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,12]],"date-time":"2020-12-12T18:09:00Z","timestamp":1607796540000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-19504-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030195038","9783030195045"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-19504-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"27 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DESRIST","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Design Science Research in Information Systems and Technology","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Worcester, MA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 June 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 June 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"desrist2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/desrist2019.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"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"54","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"20","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"37% - 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"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}