These days cyber bullying and hate speech becomes a major issue . So our objective for this task is to detect tweets associated with negative sentiments. From this dataset we classify a tweet as hate speech if it has racist or sexist tweets associated with it.
So our task here is to classify racist and sexist tweets from other tweets and filter them out. With the given twitter dataset consisting of train.csv and test.csv files where we have 31962 labeled tweets and 17191 unlabeled tweets where we train and validate on the train.csv file and then test our best possible model on the test.csv file.