Topics over Time: A NonMarkov ContinuousTime Model of Topical Trends
作者： Andrew McCallum , Xuerui Wang
DOI:
关键词:
摘要: This paper presents an LDA-style topic model that captures not only the low-dimensional structure of data, but also how changes over time. Unlike other recent work relies on Markov assumptions or discretization time, here each is associated with a continuous distribution timestamps, and for generated document, mixture topics influenced by both word co-occurrences document’s timestamp. Thus, meaning particular can be relied upon as constant, topics’ occurrence correlations change significantly We present results nine months personal email, 17 years NIPS research papers 200 presidential state-of-the-union addresses, showing improved topics, better timestamp prediction, interpretable trends.
参考文章(18)
Andrew McCallum, Xuerui Wang, A Note on Topical N-grams ,(2005)
Uri Nodelman, Christian R. Shelton, Daphne Koller, Continuous time bayesian networks ,(2007)
Andrés Corrada-Emmanuel, Andrew McCallum, Xuerui Wang, Topic and role discovery in social networks international joint conference on artificial intelligence. pp. 786- 791 ,(2005)
David M Blei, Andrew Y Ng, Michael I Jordan, None, Latent dirichlet allocation Journal of Machine Learning Research. ,vol. 3, pp. 993- 1022 ,(2003) , 10.5555/944919.944937
P. Kumaraswamy, A generalized probability density function for double-bounded random processes Journal of Hydrology. ,vol. 46, pp. 79- 88 ,(1980) , 10.1016/0022-1694(80)90036-0
T. L. Griffiths, M. Steyvers, Finding scientific topics Proceedings of the National Academy of Sciences of the United States of America. ,vol. 101, pp. 5228- 5235 ,(2004) , 10.1073/PNAS.0307752101
Xiaodan Song, Ching-Yung Lin, Belle L. Tseng, Ming-Ting Sun, Modeling and predicting personal information dissemination behavior knowledge discovery and data mining. pp. 479- 488 ,(2005) , 10.1145/1081870.1081925
Jon Kleinberg, Bursty and hierarchical structure in streams Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '02. pp. 91- 101 ,(2002) , 10.1145/775047.775061
Purnamrita Sarkar, Andrew W. Moore, Dynamic social network analysis using latent space models Sigkdd Explorations. ,vol. 7, pp. 31- 40 ,(2005) , 10.1145/1117454.1117459
David M. Blei, John D. Lafferty, Dynamic topic models Proceedings of the 23rd international conference on Machine learning - ICML '06. pp. 113- 120 ,(2006) , 10.1145/1143844.1143859