Sentiment Analysis with LDA
In this project, we will apply Latent Dirichlet Allocation (LDA) to classify the sentiment of text. We will use BERT (Bidirectional Encoder Representations from Transformers) to extract the features of the text and then apply LDA to classify the sentiment of the text.
We will be using the tweet_eval dataset from Hugging Face, which contains tweets with three different sentiments: positive, negative, and neutral.
This project is for MATH 3180: Mathematics for Machine Learning at the University of Connecticut.