Term Weighting in Topic Modeling

Topic modeling is a text mining technique used for automatic extraction of topics addressed in document collections. Although Latent Dirichlet Allocation (LDA) is the most preferred model in this field, some problems with its use are still unsolved. In this study, in order to contribute to the solution of these problems, the effect of using different term weights on model coherence is investigated. For this purpose, topic models using different term weights are applied to more than one scientific corpus, and model coherence scores obtained are compared with each other.