{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T16:49:24Z","timestamp":1725986964621},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319991320"},{"type":"electronic","value":"9783319991337"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-99133-7_6","type":"book-chapter","created":{"date-parts":[[2018,8,6]],"date-time":"2018-08-06T14:38:25Z","timestamp":1533566305000},"page":"76-87","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Performance Comparison of Three Spark-Based Implementations of Parallel Entity Resolution"],"prefix":"10.1007","author":[{"given":"Xiao","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kirity","family":"Rapuru","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriel Campero","family":"Durand","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eike","family":"Schallehn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gunter","family":"Saake","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,7]]},"reference":[{"key":"6_CR1","unstructured":"Apache: Apache spark. http:\/\/spark.apache.org\/ . Accessed 10 April 2018"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Armbrust, M., et al.: Spark SQL: relational data processing in spark. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, pp. 1383\u20131394. ACM (2015)","DOI":"10.1145\/2723372.2742797"},{"issue":"1","key":"6_CR3","first-page":"30","volume":"4","author":"X Chen","year":"2018","unstructured":"Chen, X., Schallehn, E., Saake, G.: Cloud-scale entity resolution: current state and open challenges. Open J. Big Data (OJBD) 4(1), 30\u201351 (2018)","journal-title":"Open J. Big Data (OJBD)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Zoun, R., Schallehn, E., Mantha, S., Rapuru, K., Saake, G.: Exploring spark-SQL-based entity resolution using the persistence capability. In: International Conference: Beyond Databases, Architectures and Structures (2018, Forthcoming)","DOI":"10.1007\/978-3-319-99987-6_1"},{"key":"6_CR5","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 Science & Business Media, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31164-2"},{"key":"6_CR6","doi-asserted-by":"publisher","unstructured":"Christen, P., Vatsalan, D.: Flexible and extensible generation and corruption of personal data. In: Proceedings of the 22nd ACM International Conference on Information & Knowledge Management, CIKM 2013, pp. 1165\u20131168. ACM, New York (2013). https:\/\/doi.org\/10.1145\/2505515.2507815","DOI":"10.1145\/2505515.2507815"},{"key":"6_CR7","unstructured":"Cohen, W., Ravikumar, P., Fienberg, S.: A comparison of string metrics for matching names and records. In: KDD Workshop on Data Cleaning and Object Consolidation, vol. 3, pp. 73\u201378 (2003)"},{"key":"6_CR8","unstructured":"Hortonworks: Hortonworks data platform. https:\/\/hortonworks.com\/products\/data-platforms\/ . Accessed 25 June 2018"},{"key":"6_CR9","volume-title":"High Performance Spark","author":"H Karau","year":"2017","unstructured":"Karau, H., Warren, R.: High Performance Spark. O\u2019Reilly Media, Sebastopol (2017)"},{"key":"6_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jss.2017.03.003","volume":"128","author":"DG Mestre","year":"2017","unstructured":"Mestre, D.G., Pires, C.E.S., Nascimento, D.C., de Queiroz, A.R.M., Santos, V.B., Araujo, T.B.: An efficient spark-based adaptive windowing for entity matching. J. Syst. Softw. 128, 1\u201310 (2017)","journal-title":"J. Syst. Softw."},{"issue":"9","key":"6_CR11","doi-asserted-by":"publisher","first-page":"684","DOI":"10.14778\/2947618.2947624","volume":"9","author":"G Papadakis","year":"2016","unstructured":"Papadakis, G., Svirsky, J., Gal, A., Palpanas, T.: Comparative analysis of approximate blocking techniques for entity resolution. Proc. VLDB Endow. 9(9), 684\u2013695 (2016). https:\/\/doi.org\/10.14778\/2947618.2947624","journal-title":"Proc. VLDB Endow."},{"key":"6_CR12","unstructured":"Pita, R., Pinto, C., Melo, P., Silva, M., Barreto, M., Rasella, D.: A spark-based workflow for probabilistic record linkage of healthcare data. In: EDBT\/ICDT Workshops, pp. 17\u201326 (2015)"},{"key":"6_CR13","doi-asserted-by":"publisher","unstructured":"Tran, K.N., Vatsalan, D., Christen, P.: GeCo: an online personal data generator and corruptor. In: Proceedings of the 22nd ACM International Conference on Information & Knowledge Management, CIKM 2013, pp. 2473\u20132476. ACM, New York (2013). https:\/\/doi.org\/10.1145\/2505515.2508207","DOI":"10.1145\/2505515.2508207"},{"key":"6_CR14","unstructured":"Wang, C., Karimi, S.: Parallel duplicate detection in adverse drug reaction databases with spark. In: EDBT, pp. 551\u2013562 (2016)"}],"container-title":["Communications in Computer and Information Science","Database and Expert Systems Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-99133-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T22:09:32Z","timestamp":1571695772000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99133-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319991320","9783319991337"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99133-7_6","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2018]]}}}