L-EnsNMF: Boosted local topic discovery via ensemble of nonnegative matrix factorization

Nonnegative matrix factorization (NMF) has beenwidely applied in many domains. In document analysis, it hasbeen increasingly used in topic modeling applications, where aset of underlying topics are revealed by a low-rank factor matrixfrom NMF. However, it is often the case that the resulting topicsgive only general topic information in the data, which tends notto convey much information. To tackle this problem, we proposea novel ensemble model of nonnegative matrix factorizationfor discovering high-quality local topics. Our method leveragesthe idea of an ensemble model, which has been successfulin supervised learning, into an unsupervised topic modelingcontext. That is, our model successively performs NMF givena residual matrix obtained from previous stages and generatesa sequence of topic sets. Our algorithm for updating the inputmatrix has novelty in two aspects. The first lies in utilizing theresidual matrix inspired by a state-of-The-Art gradient boostingmodel, and the second stems from applying a sophisticatedlocal weighting scheme on the given matrix to enhance thelocality of topics, which in turn delivers high-quality, focusedtopics of interest to users. We evaluate our proposed method bycomparing it against other topic modeling methods, such as afew variants of NMF and latent Dirichlet allocation, in termsof various evaluation measures representing topic coherence, diversity, coverage, computing time, and so on. We also presentqualitative evaluation on the topics discovered by our methodusing several real-world data sets.