{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T18:17:49Z","timestamp":1776709069233,"version":"3.51.2"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2010,8,5]],"date-time":"2010-08-05T00:00:00Z","timestamp":1280966400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2010,8,5]],"date-time":"2010-08-05T00:00:00Z","timestamp":1280966400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Inf Retrieval"],"published-print":{"date-parts":[[2011,4]]},"DOI":"10.1007\/s10791-010-9141-9","type":"journal-article","created":{"date-parts":[[2010,8,4]],"date-time":"2010-08-04T12:41:23Z","timestamp":1280925683000},"page":"178-203","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":195,"title":["Investigating task performance of probabilistic topic models: an empirical study of PLSA and LDA"],"prefix":"10.1007","volume":"14","author":[{"given":"Yue","family":"Lu","sequence":"first","affiliation":[]},{"given":"Qiaozhu","family":"Mei","sequence":"additional","affiliation":[]},{"given":"ChengXiang","family":"Zhai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2010,8,5]]},"reference":[{"key":"9141_CR1","unstructured":"Blei, D. M., Griffiths, T. L., Jordan, M. I., & Tenenbaum, J. B. (2004). Hierarchical topic models and the nested chinese restaurant process. In Advances in neural information processing systems (p. 2003). MIT Press."},{"key":"9141_CR2","unstructured":"Blei, D. M., & Lafferty, J. D. (2005). Correlated topic models. In NIPS. MIT Press"},{"key":"9141_CR3","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1162\/jmlr.2003.3.4-5.993","volume":"3","author":"D. M. Blei","year":"2003","unstructured":"Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet\u00a0allocation. Journal of Machine Learning Research, 3, 993\u20131022.","journal-title":"Journal of Machine Learning Research"},{"key":"9141_CR4","doi-asserted-by":"crossref","unstructured":"Cai, D., Mei, Q., Han, J., & Zhai, C. (2008). Modeling hidden topics on document manifold. In J. G. Shanahan, S. Amer-Yahia, I. Manolescu, Y. Zhang, D. A. Evans, A. Kolcz, K.-S. Choi, & A. Chowdhury (Eds.), CIKM (pp. 911\u2013920). ACM.","DOI":"10.1145\/1458082.1458202"},{"key":"9141_CR5","unstructured":"Chang, J., Boyd-Graber, J., Wang, C., Gerrish, S., & Blei, D. M. (2009). Reading tea leaves: How humans interpret topic models. In Neural information processing systems. MIT Press."},{"key":"9141_CR6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A. P. Dempster","year":"1977","unstructured":"Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of Royal Statistical Society, Series B, 39, 1\u201338.","journal-title":"Journal of Royal Statistical Society, Series B"},{"key":"9141_CR7","doi-asserted-by":"crossref","unstructured":"Gaussier, E., & Goutte, C. (2005). Relation between plsa and nmf and implications. In SIGIR \u201905: Proceedings of the 28th annual international ACM SIGIR conference on research and development in information retrieval (pp. 601\u2013602). New York, NY, USA: ACM.","DOI":"10.1145\/1076034.1076148"},{"issue":"6","key":"9141_CR8","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1109\/TPAMI.1984.4767596","volume":"6","author":"S. Geman","year":"1984","unstructured":"Geman, S., & Geman, D. (1984). Stochastic relaxation, gibbs distributions and the bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6(6), 721\u2013741.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9141_CR9","doi-asserted-by":"crossref","unstructured":"Girolami, M., & Kab\u00e1n, A. (2003). On an equivalence between plsi and lda. In SIGIR \u201903: Proceedings of the 26th annual international ACM SIGIR conference on research and development in informaion retrieval (pp. 433\u2013434). New York, NY, USA: ACM.","DOI":"10.1145\/860435.860537"},{"issue":"Suppl 1","key":"9141_CR10","doi-asserted-by":"publisher","first-page":"5228","DOI":"10.1073\/pnas.0307752101","volume":"101","author":"T. L. Griffiths","year":"2004","unstructured":"Griffiths, T. L., & Steyvers, M. (2004). Finding scientific topics. Proceedings of the National Academy of Sciences of the United States of America, 101(Suppl. 1), 5228\u20135235.","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"9141_CR11","unstructured":"Hofmann, T. (1999a). Probabilistic latent semantic analysis. In K. B. Laskey & H. Prade (Eds.), UAI (pp. 289\u2013296). Morgan Kaufmann."},{"key":"9141_CR12","doi-asserted-by":"crossref","unstructured":"Hofmann, T. (1999b). Probabilistic latent semantic indexing. In SIGIR \u201999: Proceedings of the 22nd annual international ACM SIGIR conference on research and development in information retrieval (pp. 50\u201357). New York, NY, USA. ACM.","DOI":"10.1145\/312624.312649"},{"key":"9141_CR13","unstructured":"Lacoste-Julien, S., Sha, F., & Jordan, M. I. (2008). Disclda: Discriminative learning for dimensionality reduction and classification. In D. Koller, D. Schuurmans, Y. Bengio, & L. Bottou (Eds.), NIPS (pp. 897\u2013904). MIT Press."},{"key":"9141_CR14","doi-asserted-by":"crossref","unstructured":"Li, W., & Mccallum, A. (2006). Pachinko allocation: Dag-structured mixture models of topic correlations. In ICML \u201906 (pp. 577\u2013584). ACM.","DOI":"10.1145\/1143844.1143917"},{"key":"9141_CR15","doi-asserted-by":"crossref","unstructured":"Mei, Q., Cai, D., Zhang, D., & Zhai, C. (2008). Topic modeling with network regularization. In WWW \u201908: Proceeding of the 17th international conference on World Wide Web (pp. 101\u2013110). New York, NY, USA: ACM.","DOI":"10.1145\/1367497.1367512"},{"key":"9141_CR16","doi-asserted-by":"crossref","unstructured":"Mei, Q., Ling, X., Wondra, M., Su, H., & Zhai, C. (2007). Topic sentiment mixture: modeling facets and opinions in weblogs. In WWW \u201907: Proceedings of the 16th international conference on World Wide Web (pp. 171\u2013180). New York, NY, USA: ACM.","DOI":"10.1145\/1242572.1242596"},{"key":"9141_CR17","doi-asserted-by":"crossref","unstructured":"Mei, Q., & Zhai, C. (2006). A mixture model for contextual text mining. In KDD \u201906: Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 649\u2013655). New York, NY, USA: ACM.","DOI":"10.1145\/1150402.1150482"},{"key":"9141_CR18","unstructured":"Minka, T. P., & Lafferty, J. D. (2002). Expectation-propogation for the generative aspect model. In A. Darwiche, & N. Friedman (Eds.), UAI (pp. 352\u2013359). Morgan Kaufmann."},{"key":"9141_CR19","doi-asserted-by":"crossref","unstructured":"Nallapati, R. M., Ahmed, A., Xing, E. P., & Cohen, W. W. (2008). Joint latent topic models for text and citations. In Proceeding of the 14th ACM SIGKDD international conference on knowledge discovery and data mining (pp. 542\u2013550). New York, NY, USA: ACM.","DOI":"10.1145\/1401890.1401957"},{"key":"9141_CR20","unstructured":"Steyvers, M., & Griffiths, T. (2007). Probabilistic topic models. Lawrence Erlbaum Associates."},{"key":"9141_CR21","doi-asserted-by":"crossref","unstructured":"Steyvers, M., Smyth, P., Rosen-Zvi, M., & Griffiths, T. (2004). Probabilistic author-topic models for information discovery. In KDD \u201904: Proceedings of the tenth ACM SIGKDD international conference on knowledge discovery and data mining (pp. 306\u2013315). New York, NY, USA: ACM.","DOI":"10.1145\/1014052.1014087"},{"key":"9141_CR22","unstructured":"Teh, Y. W., & G\u00f6r\u00fcr, D. (2009). Indian buffet processes with power-law behavior. In Advances in neural information processing systems. MIT Press."},{"key":"9141_CR23","doi-asserted-by":"crossref","unstructured":"Wallach, H. M., Murray, I., Salakhutdinov, R., & Mimno, D. (2009). Evaluation methods for topic models. In ICML \u201909: Proceedings of the 26th annual international conference on machine learning (pp. 1105\u20131112). New York, NY, USA: ACM.","DOI":"10.1145\/1553374.1553515"},{"key":"9141_CR24","doi-asserted-by":"crossref","unstructured":"Wang, X., & McCallum, A. (2006). Topics over time: A non-markov continuous-time model of topical trends. In KDD \u201906: Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining (pp. 424\u2013433). New York, NY, USA: ACM.","DOI":"10.1145\/1150402.1150450"},{"key":"9141_CR25","doi-asserted-by":"crossref","unstructured":"Wei, X., & Bruce Croft, W. (2006). Lda-based document models for ad-hoc retrieval. In SIGIR \u201906: Proceedings of the 29th annual international ACM SIGIR conference on research and development in information retrieval (pp. 178\u2013185). New York, NY, USA: ACM.","DOI":"10.1145\/1148170.1148204"},{"key":"9141_CR26","doi-asserted-by":"crossref","unstructured":"Xu, W., Liu, X., & Gong, Y. (2003). Document clustering based on non-negative matrix factorization. In SIGIR \u201903: Proceedings of the 26th annual international ACM SIGIR conference on research and development in informaion retrieval (pp. 267\u2013273). New York, NY, USA: ACM.","DOI":"10.1145\/860435.860485"},{"key":"9141_CR27","doi-asserted-by":"crossref","unstructured":"Yi, X., & Allan, J. (2009). A comparative study of utilizing topic models for information retrieval. In ECIR \u201909: Proceedings of the 31th European conference on IR research on advances in information retrieval (pp. 29\u201341). Berlin, Heidelberg: Springer.","DOI":"10.1007\/978-3-642-00958-7_6"},{"key":"9141_CR28","doi-asserted-by":"crossref","unstructured":"Zhai, C., & Lafferty, J. (2001). Model-based feedback in the language modeling approach to information retrieval. In CIKM \u201901: Proceedings of the tenth international conference on information and knowledge management (pp. 403\u2013410). New York, NY, USA: ACM.","DOI":"10.1145\/502585.502654"},{"key":"9141_CR29","doi-asserted-by":"crossref","unstructured":"Zhai, C., & Lafferty, J. (2001). A study of smoothing methods for language models applied to ad hoc information retrieval. In SIGIR \u201901: Proceedings of the 24th annual international ACM SIGIR conference on research and development in information retrieval (pp. 334\u2013342). New York, NY, USA: ACM.","DOI":"10.1145\/383952.384019"},{"key":"9141_CR30","doi-asserted-by":"crossref","unstructured":"Zhai, C., Velivelli, A., & Yu, B. (2004). A cross-collection mixture model for comparative text mining. In KDD \u201904: Proceedings of the tenth ACM SIGKDD international conference on knowledge discovery and data mining (pp. 743\u2013748). New York, NY, USA: ACM.","DOI":"10.1145\/1014052.1014150"}],"container-title":["Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-010-9141-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-010-9141-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-010-9141-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-010-9141-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,23]],"date-time":"2025-02-23T20:12:42Z","timestamp":1740341562000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-010-9141-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,8,5]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2011,4]]}},"alternative-id":["9141"],"URL":"https:\/\/doi.org\/10.1007\/s10791-010-9141-9","relation":{},"ISSN":["1386-4564","1573-7659"],"issn-type":[{"value":"1386-4564","type":"print"},{"value":"1573-7659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,8,5]]},"assertion":[{"value":"10 November 2009","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2010","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2010","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}