Uses logistic regression to make per-word predictions and evaluates if a user query sentiment is positive or negative.
Warning
The model isn't good (heavy negative bias), don't use it, it's more of a test rather than a tool.
-
Clone the repository
git clone https://github.com/l145dev/sentiment-classifier-nlp.git cd sentiment-classifier-nlp -
Open the notebook in your favorite environment
- Python
- sklearn
- Pandas
- Improve model (open ended)
Open to contributions, no guidelines, just be normal