A Machine Learning model for Hate Speech Classification
ASSUMPTIONS:
PATH TAKEN IN CODE IS THE RELATIVE PATH USED IN Google Colab. TOOL: Google Colab
- Preprocessing the text documents(the input data) using Count-Vectorizer library and converting the text into vectors.
- Spliited the data into training and validation set and applied sklearn library to test hyper parameters validation.
- After that fitted the entire data using the same sklearn library and then predicted on the test data provided after preprocessing the test data.
Key Observations:
Tested with Logistic Regression and Naive Bayes library . SVM classifier performs the best for me on my data.