{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T12:34:19Z","timestamp":1763642059710,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,4,14]],"date-time":"2016-04-14T00:00:00Z","timestamp":1460592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2016,4,14]],"date-time":"2016-04-14T00:00:00Z","timestamp":1460592000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIP-1444949"],"award-info":[{"award-number":["IIP-1444949"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1186\/s40537-016-0039-2","type":"journal-article","created":{"date-parts":[[2016,4,14]],"date-time":"2016-04-14T11:12:21Z","timestamp":1460632341000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Topic discovery and future trend forecasting for texts"],"prefix":"10.1186","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5593-1177","authenticated-orcid":false,"given":"Jose L.","family":"Hurtado","sequence":"first","affiliation":[]},{"given":"Ankur","family":"Agarwal","sequence":"additional","affiliation":[]},{"given":"Xingquan","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,4,14]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Hurtado J, Huang S, Zhu X. Topic discovery and future trend prediction using association analysis and ensemble forecasting. In: the 16th IEEE international conference on information reuse and integration. San Francisco, CA: 2015.","DOI":"10.1109\/IRI.2015.40"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Mei Q, Zhai C. Discovering evolutionary theme patterns from text: an exploration of temporal text mining. In: Proceedings of the eleventh ACM SIGKDD international conference on knowledge discovery in data mining. 2005.","DOI":"10.1145\/1081870.1081895"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Berlanga-Llavori R, Anaya-S\u00e1nchez H, Pons-Porrata A, Jim\u00e9nez-Ruiz E. Conceptual subtopic identification in the medical domain. In: Geffner H, Prada R, Machado Alexandre I, David N, editors. Advances in artificial intelligence\u2014IBERAMIA 2008. Lecture notes in computer science, vol 5290. Springer; 2008. p. 312\u201321.","DOI":"10.1007\/978-3-540-88309-8_32"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"M\u00f6rchen F, Dejori M, Fradkin D, Etienne J, Wachmann B, Bundschus M. Anticipating annotations and emerging trends in biomedical literature. In: Proc. of ACM SIG KDD conference. 2008.","DOI":"10.1145\/1401890.1402004"},{"key":"39_CR5","unstructured":"Tucker C, Kim H. Predicting emerging product design trend by mining publicly available customer review data. In: Proc. of international conference on engineering design. 2011."},{"issue":"2","key":"39_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1462198.1462204","volume":"27","author":"R Schumaker","year":"2012","unstructured":"Schumaker R, Chen H. Textual analysis of stock market prediction using breaking financial news: The azfin text system. ACM Trans Inf Syst. 2012;27(2):1\u201319.","journal-title":"ACM Trans Inf Syst."},{"issue":"6","key":"39_CR7","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1002\/asi.20342","volume":"57","author":"DJ Newman","year":"2006","unstructured":"Newman DJ, Block S. Probabilistic topic decomposition of an eighteenth-century american newspaper. J Am Soc Inf Sci Technol. 2006;57(6):753\u201367.","journal-title":"J Am Soc Inf Sci Technol"},{"issue":"4","key":"39_CR8","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1145\/2133806.2133826","volume":"55","author":"DM Blei","year":"2012","unstructured":"Blei DM. Introduction to probabilistic topic models. Commun ACM. 2012;55(4):77\u201384.","journal-title":"Commun ACM"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Fu T-c. A review on time series data mining. Eng Appl Artif Intell. 2011;24(1):164\u201381.","DOI":"10.1016\/j.engappai.2010.09.007"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Wang X, McCallum A. Topics over time: a non-markov continuous-time model of topical trends. In: Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining. 2006.","DOI":"10.1145\/1150402.1150450"},{"issue":"7043","key":"39_CR11","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1038\/nature03607","volume":"435","author":"G Palla","year":"2005","unstructured":"Palla G, Der\u00e9nyi I, Farkas I, T T.V. Uncovering the overlapping community structure of complex networks in nature and society. Nature. 2005;435(7043):814\u20138.","journal-title":"Nature."},{"issue":"5","key":"39_CR12","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1108\/EUM0000000007096","volume":"57","author":"W Mettrop","year":"2001","unstructured":"Mettrop W, Nieuwenhuysen P. Internet search engines\u2014fluctuations in document accessibility. J Doc. 2001;57(5):623\u201351.","journal-title":"J Doc"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Liu Y, Scheuermann P, Li X, Zhu X. Using wordnet to disambiguate word senses for text classification. In: international conference on computational science. 2007.","DOI":"10.1007\/978-3-540-72588-6_127"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Sussna M. Word sense disambiguation for free-text indexing using a massive semantic network. In: Proceedings of the second international conference on information and knowledge management (CIKM). 1993.","DOI":"10.1145\/170088.170106"},{"key":"39_CR15","unstructured":"Wiemer-Hastings P, Wiemer-Hastings K, Graesser A. Latent semantic analysis. Proceedings of the 16th international joint conference on artificial intelligence. 2004. p. 1\u201314."},{"key":"39_CR16","unstructured":"Joshi AC, Padghan VR, Vyawahare JR, Saner SP. Enforcing document clustering for forensic analysis using weighted matrix method (wmm). 2015."},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Jain AK. Data clustering: 50 years beyond k-means. Pattern Recognit Lett. 2010;31(8):651\u201366. Award winning papers from the 19th international conference on pattern recognition (ICPR).","DOI":"10.1016\/j.patrec.2009.09.011"},{"key":"39_CR18","unstructured":"Stein B, Eissen SMZ. Topic identification: framework and application. In: Proc of international conference on knowledge management (I-KNOW). 2004."},{"key":"39_CR19","unstructured":"Sahami M. Using machine learning to improve information access. Technical report, Stanford University; 1998."},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Jayabharathy J, Kanmani S, Parveen AA. Document clustering and topic discovery based on semantic similarity in scientific literature. In: Communication software and networks (ICCSN), 2011 IEEE 3rd international conference on. 2011. p. 425\u20139.","DOI":"10.1109\/ICCSN.2011.6014600"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Ayad H, Kamel MS. Topic discovery from text using aggregation of different clustering methods. Proceedings of the 15th conference of the Canadian society for computational studies of intelligence on advances in artificial intelligence., AI 02London, UK, UK: Springer; 2002. p. 161\u201375.","DOI":"10.1007\/3-540-47922-8_14"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Hromic H, Prangnawarat N, Hulpu\u015f I, Karnstedt M, Hayes C. Graph-based methods for clustering topics of interest in twitter. In: Engineering the web in the big data era. Lecture notes in computer science, vol 9114. Springer; 2015. p. 701\u20134.","DOI":"10.1007\/978-3-319-19890-3_61"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Wartena C, Brussee R. Topic detection by clustering keywords. In: Database and expert systems application, 2008. DEXA 08. 19th international workshop on. 2008. p. 54\u20138.","DOI":"10.1109\/DEXA.2008.120"},{"key":"39_CR24","unstructured":"Wong PC, Whitney P, Thomas J. Visualizing association rules for text mining. 1999."},{"issue":"6","key":"39_CR25","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","volume":"41","author":"S Deerwester","year":"1990","unstructured":"Deerwester S, Dumais ST, Furnas GW, Landauer TK, Harshman R. Indexing by latent semantic analysis. J Am Soc Inf Sci. 1990;41(6):391\u2013407.","journal-title":"J Am Soc Inf Sci"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Dumais ST, Furnas GW, Landauer TK, Deerwester S, Harshman R. Using latent semantic analysis to improve access to textual information. Proceedings of the SIGCHI conference on human factors in computing systems., CHI 88 New York, NY, USA: ACM; 1988. p. 281\u20135.","DOI":"10.1145\/57167.57214"},{"issue":"2\u20133","key":"39_CR27","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1080\/01638539809545028","volume":"25","author":"TK Landauer","year":"1998","unstructured":"Landauer TK, Foltz PW, Laham D. An introduction to latent semantic analysis. Discourse Process. 1998;25(2\u20133):259\u201384.","journal-title":"Discourse Process"},{"issue":"7","key":"39_CR28","first-page":"424","volume":"427","author":"M Steyvers","year":"2007","unstructured":"Steyvers M, Griffiths T. Probabilistic topic models. Handb Latent Sem Anal. 2007;427(7):424\u201340.","journal-title":"Handb Latent Sem Anal"},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Hofmann T. Probabilistic latent semantic indexing. Proceedings of the 22nd annual international ACM SIGIR conference on research and development in information retrieval, SIGIR 99New York, NY, USA: ACM; 1999. p. 50\u20137.","DOI":"10.1145\/312624.312649"},{"key":"39_CR30","doi-asserted-by":"crossref","unstructured":"Yano T, Cohen WW, Smith NA. Predicting response to political blog posts with topic models. Proceedings of human language technologies: the 2009 annual conference of the North American chapter of the association for computational linguistics, NAACL 09Stroudsburg, PA, USA: Association for Computational Linguistics; 2009. p. 477\u201385.","DOI":"10.3115\/1620754.1620824"},{"key":"39_CR31","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei DM, Ng AY, Jordan MI. Latent dirichlet allocation. J Mach Learn Res. 2003;3:993\u20131022.","journal-title":"J Mach Learn Res"},{"key":"39_CR32","doi-asserted-by":"crossref","unstructured":"Zhu D, Fukazawa Y, Karapetsas E, Ota J. Intuitive topic discovery by incorporating word-pair connection into lda. Proceedings of the the 2012 IEEE\/WIC\/ACM international joint conferences on web intelligence and intelligent agent technology-, vol 01. WI-IAT 12Washington, DC, USA: IEEE Computer Society; 2012. p. 303\u201310.","DOI":"10.1109\/WI-IAT.2012.205"},{"key":"39_CR33","doi-asserted-by":"crossref","unstructured":"Hurtado J, Taweewitchakreeya N, Zhu X. Who wrote this paper? learning for authorship de-identification using stylometric featuress. In: Information reuse and integration (IRI), 2014 IEEE 15th international conference on. 2014. p. 859\u201362.","DOI":"10.1109\/IRI.2014.7051981"},{"key":"39_CR34","doi-asserted-by":"crossref","unstructured":"Loper E, Bird S. Nltk: the natural language toolkit. Proceedings of the ACL-02 workshop on effective tools and methodologies for teaching natural language processing and computational linguistics-, vol 1. ETMTNLP 02Stroudsburg, PA, USA: Association for Computational Linguistics; 2002. p. 63\u201370.","DOI":"10.3115\/1118108.1118117"},{"key":"39_CR35","unstructured":"Toutanova K, Manning CD. Enriching the knowledge sources used in a maximum entropy part-of-speech tagger. In: Proceedings of the joint SIGDAT conference on empirical methods in natural language processing and very large corpora. 2008."},{"key":"39_CR36","volume-title":"Data mining: practical machine learning tools and techniques","author":"IH Witten","year":"2011","unstructured":"Witten IH, Frank E, Hall MA. Data mining: practical machine learning tools and techniques. 3rd ed. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc.; 2011.","edition":"3"},{"key":"39_CR37","doi-asserted-by":"crossref","unstructured":"Ravaee H, Masoudi-Nejad A, Omidi S, Moeini A. Improved immune genetic algorithm for clustering protein-protein interaction network. In: BioInformatics and bioEngineering (BIBE), 2010 IEEE international conference on. 2010. p. 174\u20139.","DOI":"10.1109\/BIBE.2010.36"},{"key":"39_CR38","unstructured":"Community P. Using the weka forecasting plugin. In: Pentaho BI suite community edition. 2011. \n                    http:\/\/wiki.pentaho.com\/display\/DATAMINING\/Using+the+Weka+Forecasting+Plugin"},{"key":"39_CR39","unstructured":"Amar Krishnay JZ, Krishnan S. Polarity trend analysis of public sentiment on youtube. In: The 19th international conference on management of data (COMAD). 2013."},{"key":"39_CR40","doi-asserted-by":"crossref","unstructured":"Tang J, Zhang J, Yao L, Li J, Zhang L, Su Z. Arnetminer: extraction and mining of academic social networks. Proceedings of the 14th ACM SIGKDD international conference on knowledge discovery and data mining, KDD 08 New York, NY, USA: ACM; 2008. p. 990\u20138.","DOI":"10.1145\/1401890.1402008"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-016-0039-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-016-0039-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-016-0039-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-016-0039-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,16]],"date-time":"2020-05-16T23:25:20Z","timestamp":1589671520000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-016-0039-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4,14]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["39"],"URL":"https:\/\/doi.org\/10.1186\/s40537-016-0039-2","relation":{},"ISSN":["2196-1115"],"issn-type":[{"type":"electronic","value":"2196-1115"}],"subject":[],"published":{"date-parts":[[2016,4,14]]},"assertion":[{"value":"13 November 2015","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2016","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 April 2016","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"7"}}