{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T04:52:51Z","timestamp":1785041571110,"version":"3.55.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031398469","type":"print"},{"value":"9783031398476","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\/978-3-031-39847-6_11","type":"book-chapter","created":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T17:02:46Z","timestamp":1692291766000},"page":"164-178","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["On Tuning the\u00a0Sorted Neighborhood Method for\u00a0Record Comparisons in\u00a0a\u00a0Data Deduplication Pipeline"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4914-9394","authenticated-orcid":false,"given":"Pawe\u0142","family":"Boi\u0144ski","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9486-929X","authenticated-orcid":false,"given":"Witold","family":"Andrzejewski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6426-3809","authenticated-orcid":false,"given":"Bartosz","family":"B\u0119bel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6037-5718","authenticated-orcid":false,"given":"Robert","family":"Wrembel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,18]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Alamuri, M., Surampudi, B.R., Negi, A.: A survey of distance\/similarity measures for categorical data. In: International Joint Conference on Neural Networks (IJCNN), pp. 1907\u20131914. IEEE (2014)","DOI":"10.1109\/IJCNN.2014.6889941"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Andrzejewski, W., B\u0119bel, B., Boi\u0144ski, P., Sienkiewicz, M., Wrembel, R.: Text similarity measures in a data deduplication pipeline for customers records. In: International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data DOLAP, co-located with EDBT\/ICDT. CEUR Workshop Proceedings, CEUR-WS.org (2023, to appear)","DOI":"10.1016\/j.is.2023.102323"},{"key":"11_CR3","unstructured":"Baxter, R., Christen, P.: A comparison of fast blocking methods for record linkage. In: ACM SIGKDD Workshop on Data Cleaning, Record Linkage, and Object Consolidation (2003)"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Bilenko, M., Kamath, B., Mooney, R.J.: Adaptive blocking: learning to scale up record linkage. In: The IEEE International Conference on Data Mining (ICDM), pp. 87\u201396. IEEE Computer Society (2006)","DOI":"10.1109\/ICDM.2006.13"},{"key":"11_CR5","unstructured":"Boi\u0144ski, P., Sienkiewicz, M., B\u0119bel, B., Wrembel, R., Ga\u0142\u0119zowski, D., Graniszewski, W.: On customer data deduplication: lessons learned from a R &D project in the financial sector. In: Workshops of the EDBT\/ICDT 2022 Joint Conference. CEUR Workshop Proceedings, vol. 3135. CEUR-WS.org (2022)"},{"key":"11_CR6","unstructured":"Boi\u0144ski, P., Sienkiewicz, M., Wrembel, R., B\u0119bel, B., Andrzejewski, W.: Text similarity measures in a data deduplication pipeline for customers records. In: ACM\/SIGAPP Symposium on Applied Computing SAC. ACM (2023, to appear)"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Boriah, S., Chandola, V., Kumar, V.: Similarity measures for categorical data: a comparative evaluation. In: SIAM International Conference on Data Mining (SDM), pp. 243\u2013254. SIAM (2008)","DOI":"10.1137\/1.9781611972788.22"},{"key":"11_CR8","unstructured":"Cao, Y., Chen, Z., Zhu, J., Yue, P., Lin, C., Yu, Y.: Leveraging unlabeled data to scale blocking for record linkage. In: International Joint Conference on Artificial Intelligence IJCAI, pp. 2211\u20132217 (2011)"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Christen, P.: A comparison of personal name matching: techniques and practical issues. In: International Conference on Data Mining (ICDM), pp. 290\u2013294. IEEE Computer Society (2006)","DOI":"10.1109\/ICDMW.2006.2"},{"key":"11_CR10","series-title":"Data-Centric Systems and Applications","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. DCSA, Springer (2012). https:\/\/doi.org\/10.1007\/978-3-642-31164-2"},{"issue":"9","key":"11_CR11","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1109\/TKDE.2011.127","volume":"24","author":"P Christen","year":"2012","unstructured":"Christen, P.: A survey of indexing techniques for scalable record linkage and deduplication. IEEE Trans. Knowl. Data Eng. 24(9), 1537\u20131555 (2012)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Christophides, V., Efthymiou, V., Palpanas, T., Papadakis, G., Stefanidis, K.: An overview of end-to-end entity resolution for big data. ACM Comput. Surv. 53(6), 127:1\u2013127:42 (2021)","DOI":"10.1145\/3418896"},{"key":"11_CR13","unstructured":"Colyer, A.: The morning paper on An overview of end-to-end entity resolution for big data (2020). https:\/\/blog.acolyer.org\/2020\/12\/14\/entity-resolution\/"},{"issue":"1","key":"11_CR14","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":"11_CR15","doi-asserted-by":"crossref","unstructured":"Kejriwal, M.: Sorted neighborhood for the semantic web. In: AAAI Conference on Artificial Intelligence, pp. 4174\u20134175. AAAI Press (2015)","DOI":"10.1609\/aaai.v29i1.9707"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Kejriwal, M., Miranker, D.P.: An unsupervised algorithm for learning blocking schemes. In: IEEE International Conference on Data Mining, pp. 340\u2013349. IEEE Computer Society (2013)","DOI":"10.1109\/ICDM.2013.60"},{"issue":"2","key":"11_CR17","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.datak.2009.10.003","volume":"69","author":"H K\u00f6pcke","year":"2010","unstructured":"K\u00f6pcke, H., Rahm, E.: Frameworks for entity matching: a comparison. Data Knowl. Eng. 69(2), 197\u2013210 (2010)","journal-title":"Data Knowl. Eng."},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Li, G., Wu, Q., Tu, D., Sun, S.: A sorted neighborhood approach for detecting duplicated regions in image forgeries based on DWT and SVD. In: IEEE International Conference on Multimedia and Expo ICME, pp. 1750\u20131753. IEEE Computer Society (2007)","DOI":"10.1109\/ICME.2007.4285009"},{"key":"11_CR19","unstructured":"Naumann, F.: Similarity Measures. Hasso Plattner Institute (2013)"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Papadakis, G., Skoutas, D., Thanos, E., Palpanas, T.: Blocking and filtering techniques for entity resolution: a survey. ACM Comput. Surv. 53(2), 31:1\u201331:42 (2020)","DOI":"10.1145\/3377455"},{"issue":"4","key":"11_CR21","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1145\/3385658.3385664","volume":"48","author":"G Papadakis","year":"2019","unstructured":"Papadakis, G., Tsekouras, L., Thanos, E., Giannakopoulos, G., Palpanas, T., Koubarakis, M.: Domain- and structure-agnostic end-to-end entity resolution with JedAI. SIGMOD Rec. 48(4), 30\u201336 (2019)","journal-title":"SIGMOD Rec."},{"issue":"2","key":"11_CR22","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1093\/comjnl\/7.2.155","volume":"7","author":"MJD Powell","year":"1964","unstructured":"Powell, M.J.D.: An efficient method for finding the minimum of a function of several variables without calculating derivatives. Comput. J. 7(2), 155\u2013162 (1964)","journal-title":"Comput. J."},{"key":"11_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1007\/11687238_46","volume-title":"Advances in Database Technology - EDBT 2006","author":"S Puhlmann","year":"2006","unstructured":"Puhlmann, S., Weis, M., Naumann, F.: XML duplicate detection using sorted neighborhoods. In: Ioannidis, Y., et al. (eds.) EDBT 2006. LNCS, vol. 3896, pp. 773\u2013791. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11687238_46"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Ramadan, B., Christen, P., Liang, H., Gayler, R.W.: Dynamic sorted neighborhood indexing for real-time entity resolution. ACM J. Data Inf. Qual. 6(4), 15:1\u201315:29 (2015)","DOI":"10.1145\/2816821"},{"key":"11_CR25","unstructured":"Sienkiewicz, M., Wrembel, R.: Managing data in a big financial institution: conclusions from a R &D project. In: Workshops of the EDBT\/ICDT 2021 Joint Conference. CEUR Workshop Proceedings, vol. 2841. CEUR-WS.org (2021)"},{"key":"11_CR26","unstructured":"de Souza Silva, L., Murai, F., da Silva, A.P.C., Moro, M.M.: Automatic identification of best attributes for indexing in data deduplication. In: Mendelzon, A. (ed.) International Workshop on Foundations of Data Management. CEUR Workshop Proceedings, vol. 2100. CEUR-WS.org (2018)"},{"key":"11_CR27","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/978-3-642-37456-2_29","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"D Vatsalan","year":"2013","unstructured":"Vatsalan, D., Christen, P.: Sorted nearest neighborhood clustering for efficient private blocking. In: Pei, J., Tseng, V.S., Cao, L., Motoda, H., Xu, G. (eds.) PAKDD 2013. LNCS (LNAI), vol. 7819, pp. 341\u2013352. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37456-2_29"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Yan, S., Lee, D., Kan, M., Giles, C.L.: Adaptive sorted neighborhood methods for efficient record linkage. In: ACM\/IEEE Joint Conference on Digital Libraries JCDL, pp. 185\u2013194. ACM (2007)","DOI":"10.1145\/1255175.1255213"}],"container-title":["Lecture Notes in Computer Science","Database and Expert Systems Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-39847-6_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:27:27Z","timestamp":1710332847000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-39847-6_11"}},"subtitle":["Industrial Experience Report"],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031398469","9783031398476"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-39847-6_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"18 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DEXA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database and Expert Systems Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Penang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malaysia","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":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dexa2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dexa.org\/dexa2023","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":"EquinOCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"155","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":"49","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":"35","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":"32% - 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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the workshops 7 full and 3 short papers have been accepted from 20 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}