Topic modeling, as we have seen in the previous example, is not mutually exclusive as it models documents as a mixture of topics. For example, a document can be categorized as 70% Topic A and 30% Topic B. Text classification, on the other hand, classifies documents exclusively belonging to a specific class. However, this requires labeled data that may not always be available. It is also possible to use the output of a topic model as a feature for text classification which might improve the classification's accuracy. Topic models can also be used to quickly create manual labeled data that can be subsequently used for training a text classifier. We have touched upon topic modeling and have seen how it differs from text classification or complements it. Let's now explore text classification using deep learning models.