This item is available under a Creative Commons License for non-commercial use only
In this paper we present a two-pass algorithm based on different matrix decompositions, such as LSI, PCA, ICA and NMF, which allows tracking of the evolution of topics over time. The proposed dynamic topic models as output give an easily interpreted overview of topics found in a sequentially organized set of documents that does not require further processing. Each topic is presented by a user-specified number of top-terms. Such an approach to topic modeling if applied to, for example, a news article data set, can be convenient and useful for economists, sociologists, political scientists. The proposed approach allows to achieve results comparable to those obtained using complex probabilistic models, such as LDA.
SSkitalinskaya G., Alexandrov M., Cardiff J. (2018) Comparison of two-pass algorithms for dynamic topic modeling based on matrix decompositions. In: (Castro F., Miranda-Jiménez S., González-Mendoza M. (eds)) Advances in Computational Intelligence. MICAI 2017. Lecture Notes in Computer Science, vol 10633. Springer. doi:10.1007/978-3-030-02840-4_3