{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T01:51:03Z","timestamp":1742953863351,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031469930"},{"type":"electronic","value":"9783031469947"}],"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\/978-3-031-46994-7_20","type":"book-chapter","created":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T07:02:16Z","timestamp":1698303736000},"page":"238-252","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Diversity Similarity Join for Big Data"],"prefix":"10.1007","author":[{"given":"Yasin N.","family":"Silva","sequence":"first","affiliation":[]},{"given":"Juan","family":"Martinez","sequence":"additional","affiliation":[]},{"given":"Pedro","family":"Castro Cea","sequence":"additional","affiliation":[]},{"given":"Humberto","family":"Razente","sequence":"additional","affiliation":[]},{"given":"Maria C.","family":"Nardini Barioni","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"B\u00f6hm, C., Braunm\u00fcller, B., Krebs, F., Kriegel, H.-P.: Epsilon grid order: an algorithm for the similarity join on massive high-dimensional data. In: SIGMOD (2001)","DOI":"10.1145\/375663.375714"},{"key":"20_CR2","doi-asserted-by":"publisher","unstructured":"Santos, L.F.D., Carvalho, L.O., Oliveira, W.D., Traina, A.J.M., Traina Jr., C.: Diversity in similarity joins. In: Amato, G., Connor, R., Falchi, F., Gennaro, C. (eds.) SISAP 2015. LNCS, vol. 9371, pp. 42\u201353. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-25087-8_4","DOI":"10.1007\/978-3-319-25087-8_4"},{"key":"20_CR3","unstructured":"Apache. Spark. https:\/\/spark.apache.org\/"},{"key":"20_CR4","unstructured":"SimCloud Research Team. D2SJ Source Code. https:\/\/ysilva.cs.luc.edu\/SimCloud\/downloads.html"},{"key":"20_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/978-3-540-45227-0_48","volume-title":"Database and Expert Systems Applications","author":"V Dohnal","year":"2003","unstructured":"Dohnal, V., Gennaro, C., Zezula, P.: Similarity join in metric spaces using ED-Index. In: Ma\u0159\u00edk, V., Retschitzegger, W., \u0160t\u011bp\u00e1nkov\u00e1, O. (eds.) DEXA 2003. LNCS, vol. 2736, pp. 484\u2013493. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/978-3-540-45227-0_48"},{"key":"20_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1007\/3-540-36618-0_32","volume-title":"Advances in Information Retrieval","author":"V Dohnal","year":"2003","unstructured":"Dohnal, V., Gennaro, C., Savino, P., Zezula, P.: Similarity join in metric spaces. In: Sebastiani, F. (ed.) ECIR 2003. LNCS, vol. 2633, pp. 452\u2013467. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-36618-0_32"},{"issue":"2","key":"20_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1366102.1366104","volume":"33","author":"EH Jacox","year":"2008","unstructured":"Jacox, E.H., Samet, H.: Metric space similarity joins. ACM Trans. Database Syst. 33(2), 1\u201338 (2008). https:\/\/doi.org\/10.1145\/1366102.1366104","journal-title":"ACM Trans. Database Syst."},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Silva, Y.N., Reed, J.M., Tsosie, L.M.: MapReduce-based similarity join for metric spaces. In: VLDB\/Cloud-I (2012)","DOI":"10.1145\/2347673.2347676"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Hjaltason, G.R., Samet, H.: Incremental distance join algorithms for spatial databases. In: SIGMOD (1998)","DOI":"10.1145\/276304.276326"},{"key":"20_CR10","first-page":"728","volume":"6","author":"C B\u00f6hm","year":"2004","unstructured":"B\u00f6hm, C., Krebs, F.: The k-nearest neighbour join: turbo charging the KDD process. KAIS 6, 728\u2013749 (2004)","journal-title":"KAIS"},{"key":"20_CR11","unstructured":"Apache. Hadoop. https:\/\/hadoop.apache.org\/"},{"key":"20_CR12","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. In: OSDI (2004)"},{"key":"20_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/978-3-319-46759-7_14","volume-title":"Similarity Search and Applications","author":"YN Silva","year":"2016","unstructured":"Silva, Y.N., Reed, J., Brown, K., Wadsworth, A., Rong, C.: An experimental survey of MapReduce-based similarity joins. In: Amsaleg, L., Houle, M.E., Schubert, E. (eds.) SISAP 2016. LNCS, vol. 9939, pp. 181\u2013195. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46759-7_14"},{"issue":"10","key":"20_CR14","doi-asserted-by":"publisher","first-page":"1110","DOI":"10.14778\/3231751.3231760","volume":"11","author":"F Fier","year":"2018","unstructured":"Fier, F., Augsten, N., Bouros, P., Leser, U., Freytag, J.-C.: Set similarity joins on MapReduce: an experimental survey. Proc. VLDB Endow. 11(10), 1110\u20131122 (2018). https:\/\/doi.org\/10.14778\/3231751.3231760","journal-title":"Proc. VLDB Endow."},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Afrati, F.N., Sarma, A.D., Menestrina, D., Parameswaran, A., Ullman, J.D.: Fuzzy joins using MapReduce. In: ICDE (2012)","DOI":"10.1109\/ICDE.2012.66"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Vernica, R., Carey, M.J., Li, C.: Efficient parallel set-similarity joins using MapReduce. In: SIGMOD (2010)","DOI":"10.1145\/1807167.1807222"},{"issue":"8","key":"20_CR17","doi-asserted-by":"publisher","first-page":"704","DOI":"10.14778\/2212351.2212353","volume":"5","author":"A Metwally","year":"2012","unstructured":"Metwally, A., Faloutsos, C.: V-SMART-join: a scalable MapReduce framework for all-pair similarity joins of multisets and vectors. Proc. VLDB Endow. 5(8), 704\u2013715 (2012). https:\/\/doi.org\/10.14778\/2212351.2212353","journal-title":"Proc. VLDB Endow."},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Silva, Y.N., Reed, J.M.: Exploiting MapReduce-based similarity joins. In: SIGMOD (2012)","DOI":"10.1145\/2213836.2213935"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Okcan, A., Riedewald, M.: Processing theta-joins using MapReduce. In: SIGMOD (2011)","DOI":"10.1145\/1989323.1989423"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Drosou, M., Pitoura, E.: DisC diversity: result diversification based on dissimilarity and coverage. In: CIKM (2010)","DOI":"10.1145\/1860702.1860709"},{"key":"20_CR21","first-page":"57","volume":"42","author":"MR Vieira","year":"2014","unstructured":"Vieira, M.R., et al.: On query result diversification. Inf. Syst. 42, 57\u201377 (2014)","journal-title":"Inf. Syst."},{"key":"20_CR22","unstructured":"Ge, X., Chrysanthis, P.K.: PrefDiv: efficient algorithms for effective top-k result diversification. In: EDBT (2020)"},{"key":"20_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-030-32047-8_19","volume-title":"Similarity Search and Applications","author":"YN Silva","year":"2019","unstructured":"Silva, Y.N., Sandoval, M., Prado, D., Wallace, X., Rong, C.: Similarity grouping in big data systems. In: Amato, G., Gennaro, C., Oria, V., Radovanovi\u0107, M. (eds.) SISAP 2019. LNCS, vol. 11807, pp. 212\u2013220. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32047-8_19"},{"key":"20_CR24","unstructured":"Bolettieri, P., et al.: CoPhIR: A Test Collection for Content-Based Image Retrieval. arXiv:0905.4627 (2009)"},{"key":"20_CR25","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1145\/958942.958948","volume":"28","author":"GR Hjaltason","year":"2003","unstructured":"Hjaltason, G.R., Samet, H.: Index-driven similarity search in metric spaces (survey article). TODS 28, 517\u2013580 (2003)","journal-title":"TODS"}],"container-title":["Lecture Notes in Computer Science","Similarity Search and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46994-7_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T07:04:53Z","timestamp":1698303893000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46994-7_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031469930","9783031469947"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46994-7_20","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":"27 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SISAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Similarity Search and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Coruna","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":"9 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sisap2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.sisap.org\/2023\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33","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":"16","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":"4","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":"48% - 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":"2","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":"Familiarity, LaTeX and LNCS friendly, steering committee has subscription","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)"}}]}}