{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:42:54Z","timestamp":1763458974530,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,2,2]],"date-time":"2018-02-02T00:00:00Z","timestamp":1517529600000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1218043 and CNS-1405688"],"award-info":[{"award-number":["IIS-1218043 and CNS-1405688"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,2,2]]},"DOI":"10.1145\/3018661.3018727","type":"proceedings-article","created":{"date-parts":[[2017,2,2]],"date-time":"2017-02-02T15:09:48Z","timestamp":1486048188000},"page":"221-230","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Partitioning and Segment Organization Strategies for Real-Time Selective Search on Document Streams"],"prefix":"10.1145","author":[{"given":"Yulu","family":"Wang","sequence":"first","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}]},{"given":"Jimmy","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, ON, Canada"}]}],"member":"320","published-online":{"date-parts":[[2017,2,2]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"StreamKM++: A clustering algorithm for data streams. Journal of Experimental Algorithmics, 17(2):Article 2.4","author":"Ackermann M. R.","year":"2012","unstructured":"M. R. Ackermann, M. M\\\"artens, C. Raupach, K. Swierkot, C. Lammersen, and C. Sohler. StreamKM++: A clustering algorithm for data streams. Journal of Experimental Algorithmics, 17(2):Article 2.4, 2012."},{"key":"e_1_3_2_1_2_1","first-page":"10","volume-title":"NIPS","author":"Ailon N.","year":"2009","unstructured":"N. Ailon, R. Jaiswal, and C. Monteleoni. Streaming k-means approximation. NIPS, pp. 10--18, 2009."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2484028.2484033"},{"key":"e_1_3_2_1_4_1","first-page":"1027","volume-title":"SODA","author":"Arthur D.","year":"2007","unstructured":"D. Arthur and S. Vassilvitskii. k-means++: the advantages of careful seeding. SODA, pp. 1027--1035, 2007."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2484028.2484132"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2007.367846"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1571971"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.14778\/2180912.2180915"},{"key":"e_1_3_2_1_9_1","first-page":"44","volume-title":"JMLR: Workshop and Conference Proceedings 11","author":"Bifet A.","year":"2010","unstructured":"A. Bifet, G. Holmes, B. Pfahringer, P. Kranen, H. Kremer, T. Jansen, and T. Seidl. MOA: Massive Online Analysis, a framework for stream classification and clustering. JMLR: Workshop and Conference Proceedings 11, pp. 44--50, 2010."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973082.3"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2012.149"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148233"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1572013"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1718487.1718538"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-016-9279-1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609575"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/243199.243216"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0271(71)90051-9"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2914689"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1871437.1871497"},{"key":"e_1_3_2_1_22_1","volume-title":"Selective search: Efficient and effective search of large textual collections. ACM TOIS, 33(4):Article 17","author":"Kulkarni A.","year":"2015","unstructured":"A. Kulkarni and J. Callan. Selective search: Efficient and effective search of large textual collections. ACM TOIS, 33(4):Article 17, 2015."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2396761.2396833"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076087"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/354756.354830"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1321440.1321457"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1386118.1386125"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA478609"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1008992.1009026"},{"key":"e_1_3_2_1_30_1","volume-title":"MLlib: Machine learning in Apache Spark. arXiv:1505.06807v1","author":"Meng X.","year":"2015","unstructured":"X. Meng, J. Bradley, B. Yavuz, E. Sparks, S. Venkataraman, D. Liu, J. Freeman, D. Tsai, M. Amde, S. Owen, D. Xin, R. Xin, M. J. Franklin, R. Zadeh, M. Zaharia, and A. Talwalkar. MLlib: Machine learning in Apache Spark. arXiv:1505.06807v1, 2015."},{"key":"e_1_3_2_1_31_1","first-page":"746","volume-title":"NAACL\/HLT","author":"Mikolov T.","year":"2013","unstructured":"T. Mikolov, W. tau Yih, and G. Zweig. Linguistic regularities in continuous space word representations. NAACL\/HLT, pp. 746--751, 2013."},{"key":"e_1_3_2_1_32_1","volume-title":"TREC","author":"Ounis I.","year":"2011","unstructured":"I. Ounis, C. Macdonald, J. Lin, and I. Soboroff. Overview of the TREC-2011 Microblog Track. TREC, 2011."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_34_1","first-page":"25","volume-title":"The Edinburgh Twitter Corpus. NAACL\/HLT Workshop on Social Media","author":"Petrovic S.","year":"2010","unstructured":"S. Petrovic, M. Osborne, and V. Lavrenko. The Edinburgh Twitter Corpus. NAACL\/HLT Workshop on Social Media, pp. 25--26, 2010."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1146847.1146881"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71496-5_17"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000010"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/860435.860490"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2522968.2522981"},{"key":"e_1_3_2_1_40_1","volume-title":"TREC","author":"Soboroff I.","year":"2012","unstructured":"I. Soboroff, I. Ounis, C. Macdonald, and J. Lin. Overview of the TREC-2012 Microblog Track. TREC, 2012."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2010045"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505710"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1572014"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2433396.2433407"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/253495.253524"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/2964060.2964098"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312687"}],"event":{"name":"WSDM 2017: Tenth ACM International Conference on Web Search and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Cambridge United Kingdom","acronym":"WSDM 2017"},"container-title":["Proceedings of the Tenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3018661.3018727","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3018661.3018727","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3018661.3018727","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:38:11Z","timestamp":1763458691000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3018661.3018727"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,2]]},"references-count":47,"alternative-id":["10.1145\/3018661.3018727","10.1145\/3018661"],"URL":"https:\/\/doi.org\/10.1145\/3018661.3018727","relation":{},"subject":[],"published":{"date-parts":[[2017,2,2]]},"assertion":[{"value":"2017-02-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}