Dynamic Topic Models (DTM) are a variant of topic modeling that extend traditional static topic models (like Latent Dirichlet Allocation, or LDA) to account for the evolution of topics over time. Traditional topic models identify themes in a collection of documents, but they typically analyze the documents as a static set, treating their content as a snapshot without considering any temporal aspects. DTM, on the other hand, is designed to analyze a corpus of documents that spans multiple time periods.
New to topics? Read the docs here!