Detecting Hate speech from Twitter Data using ML and NLP techniques
In this Project we have taken the Dataset from Kaggle which almost have 56K lines.
Performed Data preprocessing steps such as: Lemmitization Tokenization Removing Symbols and Special Charatcters using "regex" modulr Removes duplicates from the data Converted all the letters into lowercase
Then Transformed the data using Data Vectorization after that used a Machine learning model to predict the data and got 90.53% accuracy score.
Later visualized the calcuated the metrics of the model.