Repository for Text Analytics project 2023/2024.
The goal of this project is to create a topic modeling text classifier that classifies films into different genres based on the film title and description. We would also like to output a probabilistic index that represents how much a film belongs to a genre. It might be interesting to see which values are easier to identify and which are not, how the linguistic features of the descriptions can be linked with a specific topic, that is a genre. Such a model could be useful in real-world applications, like user recommendations or automatic genre recognition on streaming platforms.