{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:42:01Z","timestamp":1761597721176,"version":"3.37.3"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2016,6,17]],"date-time":"2016-06-17T00:00:00Z","timestamp":1466121600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61473194"],"award-info":[{"award-number":["61473194"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. &amp; Cyber."],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1007\/s13042-016-0556-5","type":"journal-article","created":{"date-parts":[[2016,6,17]],"date-time":"2016-06-17T03:59:01Z","timestamp":1466135941000},"page":"1751-1766","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Ensemble subspace clustering of text data using two-level features"],"prefix":"10.1007","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5763-9743","authenticated-orcid":false,"given":"He","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Salman","family":"Salloum","sequence":"additional","affiliation":[]},{"given":"Yeshou","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Joshua Zhexue","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,6,17]]},"reference":[{"key":"556_CR1","doi-asserted-by":"publisher","unstructured":"Aggarwal CC (2015) Data mining\u2014the textbook. Springer, Berlin. doi: 10.1007\/978-3-319-14142-8","DOI":"10.1007\/978-3-319-14142-8"},{"key":"556_CR2","unstructured":"Bellman RE (2015) Adaptive control processes: a guided tour. Princeton University Press, Princeton"},{"key":"556_CR3","doi-asserted-by":"publisher","unstructured":"Bhattacharya I, Getoor L (2006) A latent dirichlet model for unsupervised entity resolution. In: Proceedings of the sixth SIAM international conference on data mining, April 20\u201322, 2006, Bethesda, MD, USA, pp 47\u201358. doi: 10.1137\/1.9781611972764.5","DOI":"10.1137\/1.9781611972764.5"},{"key":"556_CR4","doi-asserted-by":"publisher","unstructured":"Blei DM (2012) Probabilistic topic models. Commun ACM 55(4):77\u201384. doi: 10.1145\/2133806.2133826","DOI":"10.1145\/2133806.2133826"},{"key":"556_CR5","doi-asserted-by":"publisher","unstructured":"Blei DM (2014) Build, compute, critique, repeat: data analysis with latent variable models. Annu Rev Stat Appl 1(1):203\u2013232. doi: 10.1146\/annurev-statistics-022513-115657","DOI":"10.1146\/annurev-statistics-022513-115657"},{"key":"556_CR6","unstructured":"Blei DM, Ng AY, Jordan MI (2003) Latent dirichlet allocation. J Mach Learn Res 3, 993\u20131022. http:\/\/www.jmlr.org\/papers\/v3\/blei03a.html"},{"key":"556_CR7","doi-asserted-by":"publisher","unstructured":"Cai Y, Chen X, Peng PX, Huang JZ (2014) A LDA feature grouping method for subspace clustering of text data. In: Intelligence and security informatics\u2014Pacific Asia workshop, PAISI 2014, Tainan, Taiwan, May 13, 2014. Proceedings, pp 78\u201390 (2014). doi: 10.1007\/978-3-319-06677-6_7","DOI":"10.1007\/978-3-319-06677-6_7"},{"key":"556_CR8","doi-asserted-by":"publisher","unstructured":"Cai Y, Zhao H (2016) GitHub download link of the experimental text data sets. doi: 10.5281\/zenodo.48688","DOI":"10.5281\/zenodo.48688"},{"key":"556_CR9","doi-asserted-by":"publisher","unstructured":"Cha Y, Bi B, Hsieh C, Cho J (2013) Incorporating popularity in topic models for social network analysis. In: The 36th international ACM SIGIR conference on research and development in Information retrieval, SIGIR \u201913, Dublin, Ireland\u2014July 28\u2014August 01, 2013, pp 223\u2013232. doi: 10.1145\/2484028.2484086","DOI":"10.1145\/2484028.2484086"},{"key":"556_CR10","doi-asserted-by":"publisher","unstructured":"Chaney AJ, Blei DM, Eliassi-Rad T (2015) A probabilistic model for using social networks in personalized item recommendation. In: Proceedings of the 9th ACM conference on recommender systems, RecSys 2015, Vienna, Austria, September 16\u201320, 2015, pp 43\u201350. doi: 10.1145\/2792838.2800193","DOI":"10.1145\/2792838.2800193"},{"key":"556_CR11","doi-asserted-by":"publisher","unstructured":"Chen X, Xu X, Huang JZ, Ye Y (2013) Tw-k-means: automated two-level variable weighting clustering algorithm for multiview data. IEEE Trans Knowl Data Eng 25(4), 932\u2013944. doi: 10.1109\/TKDE.2011.262","DOI":"10.1109\/TKDE.2011.262"},{"key":"556_CR12","doi-asserted-by":"publisher","unstructured":"Chen X, Ye Y, Xu X, Huang JZ (2012) A feature group weighting method for subspace clustering of high-dimensional data. Pattern Recognit 45(1), 434\u2013446 (2012). doi: 10.1016\/j.patcog.2011.06.004","DOI":"10.1016\/j.patcog.2011.06.004"},{"key":"556_CR13","doi-asserted-by":"crossref","unstructured":"Cheng H, Hua KA, Vu K (2008) Constrained locally weighted clustering. PVLDB 1(1):90\u2013101. http:\/\/www.vldb.org\/pvldb\/1\/1453871.pdf","DOI":"10.14778\/1453856.1453871"},{"key":"556_CR14","doi-asserted-by":"publisher","unstructured":"Crain SP, Zhou K, Yang S, Zha H (2012) Dimensionality reduction and topic modeling: from latent semantic indexing to latent dirichlet allocation and beyond. In: Mining text data, pp 129\u2013161. doi: 10.1007\/978-1-4614-3223-4_5","DOI":"10.1007\/978-1-4614-3223-4_5"},{"key":"556_CR15","doi-asserted-by":"crossref","unstructured":"Deerwester SC, Dumais ST, Landauer TK, Furnas GW, Harshman RA (1990) Indexing by latent semantic analysis. JASIS 41(6):391\u2013407. doi:10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"556_CR16","doi-asserted-by":"publisher","unstructured":"Domeniconi C, Al-Razgan M (2009) Weighted cluster ensembles: methods and analysis. TKDD 2(4). doi: 10.1145\/1460797.1460800","DOI":"10.1145\/1460797.1460800"},{"key":"556_CR17","unstructured":"Fern XZ, Brodley CE (2003) Random projection for high dimensional data clustering: a cluster ensemble approach. In: Machine learning, proceedings of the twentieth international conference (ICML 2003), August 21\u201324, 2003, Washington, DC, USA, pp 186\u2013193. http:\/\/www.aaai.org\/Library\/ICML\/2003\/icml03-027.php"},{"key":"556_CR18","doi-asserted-by":"publisher","unstructured":"Fu X, Yang K, Huang JZ, Cui L (2015) Dynamic non-parametric joint sentiment topic mixture model. Knowl. Based Syst. 82:102\u2013114. doi: 10.1016\/j.knosys.2015.02.021","DOI":"10.1016\/j.knosys.2015.02.021"},{"key":"556_CR19","doi-asserted-by":"publisher","unstructured":"Gordon AD, Vichi M (2001) Fuzzy partition models for fitting a set of partitions. Psychometrika 66(2):229\u2013247. doi: 10.1007\/BF02294837","DOI":"10.1007\/BF02294837"},{"key":"556_CR20","doi-asserted-by":"publisher","unstructured":"Griffiths TL, Steyvers M (2004) Finding scientific topics. Proc Natl Acad Sci 101(suppl 1), 5228\u20135235. doi: 10.1073\/pnas.0307752101","DOI":"10.1073\/pnas.0307752101"},{"key":"556_CR21","doi-asserted-by":"publisher","unstructured":"He YL, Wang XZ, Huang JZ (2016) Fuzzy nonlinear regression analysis using a random weight network. Inf Sci. doi: 10.1016\/j.ins.2016.01.037","DOI":"10.1016\/j.ins.2016.01.037"},{"key":"556_CR22","doi-asserted-by":"publisher","unstructured":"Huang JZ, Ng MK, Rong H, Li Z (2005) Automated variable weighting in k-means type clustering. IEEE Trans Pattern Anal Mach Intell 27(5):657\u2013668. doi: 10.1109\/TPAMI.2005.95","DOI":"10.1109\/TPAMI.2005.95"},{"key":"556_CR23","doi-asserted-by":"publisher","unstructured":"Jing L, Ng MK, Huang JZ (2007) An entropy weighting k-means algorithm for subspace clustering of high-dimensional sparse data. IEEE Trans Knowl Data Eng 19(8):1026\u20131041. doi: 10.1109\/TKDE.2007.1048","DOI":"10.1109\/TKDE.2007.1048"},{"key":"556_CR24","doi-asserted-by":"publisher","unstructured":"Jing L, Ng MK, Xu J, Huang JZ (2005) Subspace clustering of text documents with feature weighting k-means algorithm. In: Advances in knowledge discovery and data mining, 9th Pacific-Asia conference, PAKDD 2005, Hanoi, Vietnam, May 18\u201320, 2005, proceedings, pp 802\u2013812. doi: 10.1007\/11430919_94","DOI":"10.1007\/11430919_94"},{"key":"556_CR25","doi-asserted-by":"publisher","unstructured":"Karypis G, Kumar V (1998) A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM J Sci Comput 20(1):359\u2013392. doi: 10.1137\/S1064827595287997","DOI":"10.1137\/S1064827595287997"},{"key":"556_CR26","doi-asserted-by":"publisher","unstructured":"Khan I, Huang JZ, Tung NT, Williams GJ (2014) Ensemble clustering of high dimensional data with fastmap projection. In: Trends and applications in knowledge discovery and data mining\u2014PAKDD 2014 international workshops: DANTH, BDM, MobiSocial, BigEC, CloudSD, MSMV-MBI, SDA, DMDA-Health, ALSIP, SocNet, DMBIH, BigPMA, Tainan, Taiwan, May 13\u201316, 2014. Revised selected papers, pp 483\u2013493. doi: 10.1007\/978-3-319-13186-3_43","DOI":"10.1007\/978-3-319-13186-3_43"},{"key":"556_CR27","doi-asserted-by":"publisher","unstructured":"Kriegel H, Kr\u00f6ger P, Zimek A (2009) Clustering high-dimensional data: a survey on subspace clustering, pattern-based clustering, and correlation clustering. TKDD 3(1). doi: 10.1145\/1497577.1497578","DOI":"10.1145\/1497577.1497578"},{"key":"556_CR28","doi-asserted-by":"publisher","unstructured":"Kumar CA (2011) Reducing data dimensionality using random projections and fuzzy k-means clustering. Int J Intell Comput Cybern 4(3):353\u2013365. doi: 10.1108\/17563781111160020","DOI":"10.1108\/17563781111160020"},{"key":"556_CR29","doi-asserted-by":"publisher","unstructured":"Kuncheva LI, Hadjitodorov ST (2004) Using diversity in cluster ensembles. In: Proceedings of the IEEE international conference on systems, man & cybernetics, The Hague, The Netherlands, 10\u201313 October 2004, pp 1214\u20131219. doi: 10.1109\/ICSMC.2004.1399790","DOI":"10.1109\/ICSMC.2004.1399790"},{"key":"556_CR30","doi-asserted-by":"publisher","unstructured":"Kuncheva LI, Vetrov D (2006) Evaluation of stability of k-means cluster ensembles with respect to random initialization. IEEE Trans Pattern Anal Mach Intell 28(11):1798\u20131808. doi: 10.1109\/TPAMI.2006.226","DOI":"10.1109\/TPAMI.2006.226"},{"key":"556_CR31","doi-asserted-by":"publisher","unstructured":"Law MHC, Topchy AP, Jain AK (2004) Multiobjective data clustering. In: CVPR (2), pp 424\u2013430. doi: 10.1109\/CVPR.2004.170","DOI":"10.1109\/CVPR.2004.170"},{"key":"556_CR32","unstructured":"Lewis DD (2004) RCV1-v2\/LYRL2004: the LYRL2004 distribution of the RCV1-v2 text categorization test collection. http:\/\/www.ai.mit.edu\/projects\/jmlr\/papers\/volume5\/lewis04a\/lyrl2004_rcv1v2_README.htm"},{"key":"556_CR33","unstructured":"Lewis DD (2015) Reuters-21578 text categorization test collection. http:\/\/www.daviddlewis.com\/resources\/testcollections\/reuters21578\/"},{"key":"556_CR34","unstructured":"Lewis DD, Yang Y, Rose TG, Li F (2004) RCV1: a new benchmark collection for text categorization research. J Mach Learn Res 5, 361\u2013397. http:\/\/www.ai.mit.edu\/projects\/jmlr\/papers\/volume5\/lewis04a\/lewis04a.pdf"},{"key":"556_CR35","doi-asserted-by":"publisher","unstructured":"Nagwani NK (2015) Summarizing large text collection using topic modeling and clustering based on MapReduce framework. J Big Data 2(1):1\u201318. doi: 10.1186\/s40537-015-0020-5","DOI":"10.1186\/s40537-015-0020-5"},{"key":"556_CR36","doi-asserted-by":"publisher","unstructured":"Parsons L, Haque E, Liu H (2004) Subspace clustering for high dimensional data: a review. SIGKDD Explor 6(1):90\u2013105. doi: 10.1145\/1007730.1007731","DOI":"10.1145\/1007730.1007731"},{"key":"556_CR37","doi-asserted-by":"publisher","unstructured":"Razavi AH, Inkpen D, Brusilovsky D, Bogouslavski L (2013) General topic annotation in social networks: a latent dirichlet allocation approach. In: Advances in artificial intelligence, 26th Canadian conference on artificial intelligence, Canadian AI 2013, Regina, SK, Canada, May 28\u201331, 2013. Proceedings, pp 293\u2013300. doi: 10.1007\/978-3-642-38457-8_29","DOI":"10.1007\/978-3-642-38457-8_29"},{"key":"556_CR38","unstructured":"Rennie J (2015) The 20 newsgroups data set. http:\/\/qwone.com\/jason\/20Newsgroups\/"},{"key":"556_CR39","doi-asserted-by":"publisher","unstructured":"Salton G, Wong A, Yang CS (1975) A vector space model for automatic indexing. Commun ACM 18(11):613\u2013620. doi: 10.1145\/361219.361220","DOI":"10.1145\/361219.361220"},{"key":"556_CR40","unstructured":"Strehl A, Ghosh J (2002) Cluster ensembles\u2014a knowledge reuse framework for combining multiple partitions. J Mach Learn Res 3:583\u2013617. http:\/\/www.jmlr.org\/papers\/v3\/strehl02a.html"},{"key":"556_CR41","doi-asserted-by":"publisher","unstructured":"Wang X (2015) Learning from big data with uncertainty\u2014editorial. J Intell Fuzzy Syst 28(5):2329\u20132330. doi: 10.3233\/IFS-141516","DOI":"10.3233\/IFS-141516"},{"key":"556_CR42","doi-asserted-by":"publisher","unstructured":"Wang X, Ashfaq RAR, Fu A (2015) Fuzziness based sample categorization for classifier performance improvement. J Intell Fuzzy Syst 29(3):1185\u20131196. doi: 10.3233\/IFS-151729","DOI":"10.3233\/IFS-151729"},{"key":"556_CR43","doi-asserted-by":"publisher","unstructured":"Wang X, Huang JZ (2015) Editorial: uncertainty in learning from big data. Fuzzy Sets Syst 258:1\u20134. doi: 10.1016\/j.fss.2014.10.010","DOI":"10.1016\/j.fss.2014.10.010"},{"key":"556_CR44","doi-asserted-by":"publisher","unstructured":"Wang X, Xing H, Li Y, Hua Q, Dong C, Pedrycz W (2015) A study on relationship between generalization abilities and fuzziness of base classifiers in ensemble learning. IEEE Trans Fuzzy Syst 23(5):1638\u20131654. doi: 10.1109\/TFUZZ.2014.2371479","DOI":"10.1109\/TFUZZ.2014.2371479"},{"key":"556_CR45","unstructured":"Williams G, Huang JZ, Chen X, Wang Q, Xiao L (2015) wskm: weighted k-means clustering. http:\/\/CRAN.R-project.org\/package=wskm . R package version 1.4.28"},{"key":"556_CR46","doi-asserted-by":"publisher","unstructured":"Wu J, Xiong H, Chen J (2009) Adapting the right measures for k-means clustering. In: Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining, Paris, France, June 28\u2013July 1, 2009, pp 877\u2013886. doi: 10.1145\/1557019.1557115","DOI":"10.1145\/1557019.1557115"},{"key":"556_CR47","doi-asserted-by":"publisher","unstructured":"Yin H, Cui B, Chen L, Hu Z, Zhou X (2015) Dynamic user modeling in social media systems. ACM Trans Inf Syst 33(3):10:1\u201310:44. doi: 10.1145\/2699670","DOI":"10.1145\/2699670"},{"key":"556_CR48","unstructured":"Zhang L, Mahdavi M, Jin R, Yang T, Zhu S (2013) Recovering the optimal solution by dual random projection. In: COLT 2013\u2014the 26th annual conference on learning theory, June 12\u201314, 2013. Princeton University, Princeton, pp 135\u2013157. http:\/\/jmlr.org\/proceedings\/papers\/v30\/Zhang13a.html"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13042-016-0556-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-016-0556-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-016-0556-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-016-0556-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,9]],"date-time":"2019-09-09T17:39:39Z","timestamp":1568050779000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13042-016-0556-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6,17]]},"references-count":48,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["556"],"URL":"https:\/\/doi.org\/10.1007\/s13042-016-0556-5","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2016,6,17]]}}}