{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:11:53Z","timestamp":1750219913131,"version":"3.41.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2017,3,27]],"date-time":"2017-03-27T00:00:00Z","timestamp":1490572800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61472291","41472288"],"award-info":[{"award-number":["61472291","41472288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1007\/s10115-017-1039-z","type":"journal-article","created":{"date-parts":[[2017,3,27]],"date-time":"2017-03-27T03:46:14Z","timestamp":1490586374000},"page":"507-531","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Dynamic sampling of text streams and its application in text analysis"],"prefix":"10.1007","volume":"53","author":[{"given":"Gang","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajia","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahui","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanchun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,3,27]]},"reference":[{"key":"1039_CR1","doi-asserted-by":"crossref","unstructured":"Agichtein E, Castillo C, Donato D, Gionis A, Mishne G (2008) Finding high-quality content in social media. In: Proceedings of the 1st ACM international conference on web search and data mining. ACM","DOI":"10.1145\/1341531.1341557"},{"key":"1039_CR2","doi-asserted-by":"crossref","unstructured":"Alonso O, Marshall CC, Najork M (2013) Are some tweets more interesting than others? $$\\sharp $$ \u266f Hard question. In: Proceedings of the symposium on human-computer interaction and information retrieval. ACM","DOI":"10.1145\/2528394.2528396"},{"issue":"3","key":"1039_CR3","first-page":"918","volume":"23","author":"R Baraniuk","year":"2007","unstructured":"Baraniuk R, Davenport M, DeVore R, Wakin M (2007) A simple proof of the restricted isometry property for random matrices. Constr Approx 23(3):918\u2013925","journal-title":"Constr Approx"},{"issue":"2","key":"1039_CR4","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1109\/TMM.2014.2384912","volume":"17","author":"J Bian","year":"2015","unstructured":"Bian J, Yang Y, Zhang H, Chua TS (2015) Multimedia summarization for social events in microblog stream. IEEE Trans Multimed 17(2):216\u2013228","journal-title":"IEEE Trans Multimed"},{"issue":"3","key":"1039_CR5","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1777432.1777433","volume":"28","author":"NR Brisaboa","year":"2010","unstructured":"Brisaboa NR, Faria A, Param J (2010) Dynamic lightweight text compression. ACM Trans Inf Syst 28(3):10","journal-title":"ACM Trans Inf Syst"},{"issue":"13","key":"1039_CR6","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.1002\/spe.882","volume":"38","author":"NR Brisaboa","year":"2008","unstructured":"Brisaboa NR, Faria A, Navarro G, Parama JR (2008) New adaptive compressors for natural language text. Softw Pract Exp 38(13):1429\u20131450","journal-title":"Softw Pract Exp"},{"key":"1039_CR7","doi-asserted-by":"crossref","unstructured":"Cataldi M, Caro L, Schifanella C (2010) Emerging topic detection on twitter based on temporal and social terms evaluation. In: Proceedings of the 10th international workshop in multimedia data mining","DOI":"10.1145\/1814245.1814249"},{"issue":"8","key":"1039_CR8","doi-asserted-by":"crossref","first-page":"1785","DOI":"10.3724\/SP.J.1001.2011.03857","volume":"22","author":"Y Chen","year":"2011","unstructured":"Chen Y, Cheng X, Yang S (2011) Finding high quality threads in web forums. J Softw 22(8):1785\u20131804","journal-title":"J Softw"},{"issue":"1","key":"1039_CR9","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1137\/S1064827596304010","volume":"20","author":"S Chen","year":"1998","unstructured":"Chen S, Donoho DL, Saunders MA (1998) Atomic decomposition by basis pursuit. SIAM J Sci Comput 20(1):33\u201361","journal-title":"SIAM J Sci Comput"},{"key":"1039_CR10","doi-asserted-by":"crossref","unstructured":"Choudhury MD, Counts S, Czerwinski M (2011) Find me the right content! Diversity-based sampling of social media spaces for topic-centric search. In: Proceedings of the 5th international AAAI conference on weblogs and social media","DOI":"10.1609\/icwsm.v5i1.14111"},{"issue":"2","key":"1039_CR11","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1145\/348751.348754","volume":"18","author":"E Silva de Moura","year":"2000","unstructured":"Silva de Moura E, Navarro G, Ziviani N, Baeza-Yates R (2000) Fast and flexible word searching on compressed text. ACM Trans Inf Syst 18(2):113\u2013139","journal-title":"ACM Trans Inf Syst"},{"issue":"4","key":"1039_CR12","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1109\/TIT.2006.871582","volume":"52","author":"DL Donoho","year":"2006","unstructured":"Donoho DL (2006) Compressed sensing. IEEE Trans Inf Theory 52(4):1289\u20131306","journal-title":"IEEE Trans Inf Theory"},{"key":"1039_CR13","doi-asserted-by":"crossref","unstructured":"Dutta A, Levi R, Ron D, Rubinfeld R (2013) A simple online competitive adaptation of Lempel\u2013Ziv compression with efficient random access support. In: Proceedings of the 23rd IEEE data compression conference. IEEE","DOI":"10.1109\/DCC.2013.19"},{"key":"1039_CR14","doi-asserted-by":"crossref","unstructured":"Ghosh S, Zafar MB, Bhattacharya P, Sharma N, Ganguly N, Gummadi K (2013) On sampling the wisdom of crowds: random versus expert sampling of the twitter stream. In: Proceedings of the 22nd ACM international conference on information and knowledge management. ACM","DOI":"10.1145\/2505515.2505615"},{"key":"1039_CR15","volume-title":"Data mining: concepts and techniques","author":"J Han","year":"2006","unstructured":"Han J, Kamber M (2006) Data mining: concepts and techniques, 2nd edn. Morgan Kaufmann Inc., Burlington","edition":"2"},{"issue":"3\/4","key":"1039_CR16","doi-asserted-by":"crossref","first-page":"9:1","DOI":"10.1147\/JRD.2013.2247232","volume":"57","author":"SP Kasiviswanathan","year":"2013","unstructured":"Kasiviswanathan SP, Cong G, Melville P, Lawrence RD (2013) Novel document detection for massive data streams using distributed dictionary learning. IBM J Res Dev 57(3\/4):9:1\u20139:15","journal-title":"IBM J Res Dev"},{"key":"1039_CR17","doi-asserted-by":"crossref","unstructured":"Kasiviswanathan SP, Wang H, Banerjee A, Melville P (2012) Online l1-dictionary learning with application to novel document detection. In: Proceeding of the 25th advances in neural information processing systems. MIT Press","DOI":"10.1109\/ICASSP.2013.6639341"},{"key":"1039_CR18","doi-asserted-by":"crossref","unstructured":"Meladianos P, Nikolentzos G, Rousseau F, Stavrakas Y, Vazirgiannis M (2015) Degeneracy-based real-time sub-event detection in Twitter stream. In: Proceedings of the 9th international AAAI conference on web and social media","DOI":"10.1609\/icwsm.v9i1.14597"},{"key":"1039_CR19","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. In: Proceedings of workshop at international conference on learning representations"},{"key":"1039_CR20","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado G S, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Proceedings of 27th annual conference on neural information processing systems. MIT Press"},{"issue":"2","key":"1039_CR21","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1002\/spe.4380190207","volume":"19","author":"A Moffat","year":"1989","unstructured":"Moffat A (1989) Word-based text compression. Softw Pract Exp 19(2):185\u2013198","journal-title":"Softw Pract Exp"},{"key":"1039_CR22","unstructured":"Le Q, Mikolov T (2014) Distributed representations of sentences and documents. In: Proceedings of the 31st international conference on machine learning. ACM"},{"key":"1039_CR23","doi-asserted-by":"crossref","unstructured":"Leeuwen MV, Siebes A (2008) Streamkrimp: detecting change in data streams. In: Proceedings of European conference on machine learning and principles and practice of knowledge discovery in databases. ACM","DOI":"10.1007\/978-3-540-87479-9_62"},{"issue":"2","key":"1039_CR24","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1109\/TKDE.2014.2327042","volume":"27","author":"C Li","year":"2015","unstructured":"Li C, Sun A, Weng J, He Q (2015) Tweet segmentation and its application to named entity recognition. IEEE Trans Knowl Data Eng 27(2):558\u2013570","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1039_CR25","doi-asserted-by":"crossref","unstructured":"Pati YC, Rezaiifar R, Krishnaprasad PS (1993) Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition. In: Asilomar conference on signals, systems and computers, pp 40\u201344","DOI":"10.1109\/ACSSC.1993.342465"},{"key":"1039_CR26","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.eswa.2015.08.056","volume":"44","author":"M Peng","year":"2016","unstructured":"Peng M, Gao B, Zhu J, Huang J, Yuan M, Li F (2016) High quality information extraction and query-oriented summarization for automatic query-reply in social network. Expert Syst Appl 44:92\u2013101","journal-title":"Expert Syst Appl"},{"key":"1039_CR27","doi-asserted-by":"crossref","unstructured":"Peng M, Huang J, Fu H, Zhu J, Zhou L, He Y, Li F (2013) High quality microblog extraction based on multiple features fusion and time-frequency transformation. In: Proceedings of the 14th international conference on web information systems engineering. Springer","DOI":"10.1007\/978-3-642-41154-0_14"},{"issue":"4","key":"1039_CR28","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1109\/TKDE.2012.29","volume":"25","author":"T Sakaki","year":"2013","unstructured":"Sakaki T, Okazaki M, Matsuo Y (2013) Tweet analysis for real-time event detection and earthquake reporting system development. IEEE Trans Knowl Data Eng 25(4):919\u2013931","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1039_CR29","doi-asserted-by":"crossref","unstructured":"Shrestha P, Jacquin C, Daille B (2012) Clustering short text and its evaluation. In: Proceedings of the 13th international conference on computational linguistics and intelligent text processing. Springer","DOI":"10.1007\/978-3-642-28601-8_15"},{"key":"1039_CR30","doi-asserted-by":"crossref","unstructured":"Siebes A, Vreeken J, Van Leeuwen M (2006) Item sets that compress. In: Proceedings of the 6th SIAM international conference on data mining","DOI":"10.1137\/1.9781611972764.35"},{"key":"1039_CR31","doi-asserted-by":"crossref","unstructured":"Socher R, Perelygin A, Wu JY, Chuang J, Manning CD, Ng AY, Potts C (2013) Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the conference on empirical methods in natural language processing. ACL","DOI":"10.18653\/v1\/D13-1170"},{"key":"1039_CR32","doi-asserted-by":"crossref","unstructured":"Unankard S, Li X, Sharaf MA (2015) Emerging event detection in social networks with location sensitivity. World Wide Web 18(5):1393\u20131417","DOI":"10.1007\/s11280-014-0291-3"},{"key":"1039_CR33","doi-asserted-by":"crossref","unstructured":"Xiang Y, Jin R, Fuhry D, Dragan FF (2008) Succinct summarization of transactional databases: an overlapped hyperrectangle scheme. In: Proceedings of the 14th ACM SIGKDD international conference on knowledge discovery and data mining. ACM","DOI":"10.1145\/1401890.1401981"},{"key":"1039_CR34","unstructured":"Xin D, Han J, Yan X, Cheng H (2005) Mining compressed frequent-pattern sets. In: Proceedings of the 31st international conference on very large data bases. ACM"},{"key":"1039_CR35","doi-asserted-by":"crossref","unstructured":"Yang X, Ghoting A, Ruan Y, Parthasarathy S (2012) A framework for summarizing and analyzing Twitter feeds. In: Proceedings of the 18th ACM SIGKDD international conference on knowledge discovery and data mining. ACM","DOI":"10.1145\/2339530.2339591"},{"key":"1039_CR36","doi-asserted-by":"crossref","unstructured":"Yang J, Leskovec J (2011) Patterns of temporal variation in online media. In: Proceedings of the 4th ACM international conference on web search and data mining. ACM","DOI":"10.1145\/1935826.1935863"},{"key":"1039_CR37","doi-asserted-by":"crossref","first-page":"4330","DOI":"10.1016\/j.eswa.2013.12.051","volume":"41","author":"M Yang","year":"2014","unstructured":"Yang M, Rim H (2014) Identifying interesting twitter content using topical analysis. Expert Syst Appl 41:4330\u20134336","journal-title":"Expert Syst Appl"},{"issue":"3","key":"1039_CR38","first-page":"67","volume":"36","author":"X Yang","year":"2013","unstructured":"Yang X, Ruan Y, Parthasarathy S, Ghoting A (2013) Summarization via pattern utility and ranking: a novel framework for social media data analytics. IEEE Data Eng Bull 36(3):67\u201376","journal-title":"IEEE Data Eng Bull"},{"key":"1039_CR39","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.ins.2014.01.045","volume":"285","author":"M Zihayat","year":"2014","unstructured":"Zihayat M, An A (2014) Mining top-k high utility patterns over data streams. Inf Sci 285:138\u2013161","journal-title":"Inf Sci"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-017-1039-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-017-1039-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-017-1039-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:39:36Z","timestamp":1750181976000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-017-1039-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,27]]},"references-count":39,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,11]]}},"alternative-id":["1039"],"URL":"https:\/\/doi.org\/10.1007\/s10115-017-1039-z","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"type":"print","value":"0219-1377"},{"type":"electronic","value":"0219-3116"}],"subject":[],"published":{"date-parts":[[2017,3,27]]}}}