{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T04:11:33Z","timestamp":1750824693452,"version":"3.41.0"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319635781"},{"type":"electronic","value":"9783319635798"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-63579-8_47","type":"book-chapter","created":{"date-parts":[[2017,8,2]],"date-time":"2017-08-02T05:02:42Z","timestamp":1501650162000},"page":"626-641","source":"Crossref","is-referenced-by-count":3,"title":["Improving Document Clustering for Short Texts by Long Documents via a Dirichlet Multinomial Allocation Model"],"prefix":"10.1007","author":[{"given":"Yingying","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruizhang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyuan","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,8,3]]},"reference":[{"key":"47_CR1","unstructured":"Bela, A., Frigyik, A., Gupta, M.: Introduction to the dirichlet distribution and related processes. Department of Electrical Engineering, University of Washington (2010)"},{"key":"47_CR2","unstructured":"Cheeseman, P., Kelly, J., Self, M., Stutz, J., Taylor, W., Freeman, D.: Autoclass: a Bayesian classification system. In: Readings in Knowledge Acquisition and Learning, pp. 431\u2013441. Morgan Kaufmann Publishers Inc., Burlington (1993)"},{"issue":"2","key":"47_CR3","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1111\/1467-9469.00242","volume":"28","author":"PJ Green","year":"2001","unstructured":"Green, P.J., Richardson, S.: Modelling heterogeneity with and without the dirichlet process. Scand. J. Stat. 28(2), 355\u2013375 (2001)","journal-title":"Scand. J. Stat."},{"key":"47_CR4","doi-asserted-by":"crossref","unstructured":"Hong, L., Davison, B.D.: Empirical study of topic modeling in Twitter. In: Proceedings of the First Workshop on Social Media Analytics, pp. 80\u201388. ACM (2010)","DOI":"10.1145\/1964858.1964870"},{"key":"47_CR5","doi-asserted-by":"crossref","unstructured":"Hotho, A., Staab, S., Stumme, G.: Wordnet improves text document clustering. In: Proceedings of the SIGIR 2003 Semantic Web Workshop, pp. 541\u2013544 (2003)","DOI":"10.1109\/ICDM.2003.1250972"},{"issue":"8","key":"47_CR6","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1109\/TKDE.2012.27","volume":"25","author":"R Huang","year":"2013","unstructured":"Huang, R., Yu, G., Wang, Z., Zhang, J., Shi, L.: Dirichlet process mixture model for document clustering with feature partition. IEEE Trans. Knowl. Data Eng. 25(8), 1748\u20131759 (2013)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"453","key":"47_CR7","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1198\/016214501750332758","volume":"96","author":"H Ishwaran","year":"2001","unstructured":"Ishwaran, H., James, L.F.: Gibbs sampling methods for stick-breaking priors. J. Am. Stat. Assoc. 96(453), 161\u2013173 (2001)","journal-title":"J. Am. Stat. Assoc."},{"issue":"8","key":"47_CR8","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1016\/j.patrec.2009.09.011","volume":"31","author":"AK Jain","year":"2010","unstructured":"Jain, A.K.: Data clustering: 50 years beyond k-means. Pattern Recogn. Lett. 31(8), 651\u2013666 (2010)","journal-title":"Pattern Recogn. Lett."},{"key":"47_CR9","doi-asserted-by":"crossref","unstructured":"Jin, O., Liu, N.N., Zhao, K., Yu, Y., Yang, Q.: Transferring topical knowledge from auxiliary long texts for short text clustering. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management, pp. 775\u2013784. ACM (2011)","DOI":"10.1145\/2063576.2063689"},{"issue":"7","key":"47_CR10","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1109\/TKDE.2010.27","volume":"23","author":"XH Phan","year":"2011","unstructured":"Phan, X.H., Nguyen, C.T., Le, D.T., Nguyen, L.M., Horiguchi, S., Ha, Q.T.: A hidden topic-based framework toward building applications with short web documents. IEEE Trans. Knowl. Data Eng. 23(7), 961\u2013976 (2011)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"47_CR11","doi-asserted-by":"crossref","unstructured":"Phan, X.H., Nguyen, L.M., Horiguchi, S.: Learning to classify short and sparse text & web with hidden topics from large-scale data collections. In: Proceedings of the 17th International Conference on World Wide Web, pp. 91\u2013100. ACM (2008)","DOI":"10.1145\/1367497.1367510"},{"issue":"1","key":"47_CR12","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1023\/A:1008940618127","volume":"10","author":"P Smyth","year":"2000","unstructured":"Smyth, P.: Model selection for probabilistic clustering using cross-validated likelihood. Stat. Comput. 10(1), 63\u201372 (2000)","journal-title":"Stat. Comput."},{"key":"47_CR13","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. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 990\u2013998. ACM (2008)","DOI":"10.1145\/1401890.1402008"},{"key":"47_CR14","doi-asserted-by":"crossref","unstructured":"Weng, J., Lim, E.P., Jiang, J., He, Q.: TwitterRank: finding topic-sensitive influential twitterers. In: Proceedings of the Third ACM International Conference on Web Search and Data Mining, pp. 261\u2013270. ACM (2010)","DOI":"10.1145\/1718487.1718520"},{"key":"47_CR15","doi-asserted-by":"crossref","unstructured":"Xu, J., Wang, P., Tian, G., Xu, B., Zhao, J., Wang, F., Hao, H.: Short text clustering via convolutional neural networks. In: Proceedings of NAACL-HLT, pp. 62\u201369 (2015)","DOI":"10.3115\/v1\/W15-1509"},{"key":"47_CR16","doi-asserted-by":"crossref","unstructured":"Yang, C.L., Benjamasutin, N., Chen-Burger, Y.H.: Mining hidden concepts: using short text clustering and wikipedia knowledge. In: 2014 28th International Conference on Advanced Information Networking and Applications Workshops (WAINA), pp. 675\u2013680. IEEE (2014)","DOI":"10.1109\/WAINA.2014.109"},{"key":"47_CR17","doi-asserted-by":"crossref","unstructured":"Yin, J., Wang, J.: A dirichlet multinomial mixture model-based approach for short text clustering. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 233\u2013242. ACM (2014)","DOI":"10.1145\/2623330.2623715"},{"key":"47_CR18","doi-asserted-by":"crossref","unstructured":"Yu, G., Huang, R., Wang, Z.: Document clustering via dirichlet process mixture model with feature selection. In: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 763\u2013772. ACM (2010)","DOI":"10.1145\/1835804.1835901"},{"key":"47_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1007\/978-3-642-20161-5_34","volume-title":"Advances in Information Retrieval","author":"WX Zhao","year":"2011","unstructured":"Zhao, W.X., Jiang, J., Weng, J., He, J., Lim, E.-P., Yan, H., Li, X.: Comparing Twitter and traditional media using topic models. In: Clough, P., Foley, C., Gurrin, C., Jones, G.J.F., Kraaij, W., Lee, H., Mudoch, V. (eds.) ECIR 2011. LNCS, vol. 6611, pp. 338\u2013349. Springer, Heidelberg (2011). doi: 10.1007\/978-3-642-20161-5_34"},{"issue":"1","key":"47_CR20","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10994-006-6540-7","volume":"65","author":"S Zhong","year":"2006","unstructured":"Zhong, S.: Semi-supervised model-based document clustering: a comparative study. Mach. Learn. 65(1), 3\u201329 (2006)","journal-title":"Mach. Learn."}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-63579-8_47","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T19:56:02Z","timestamp":1750794962000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-63579-8_47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319635781","9783319635798"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-63579-8_47","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}