Comparing various classifier models to find the most accurate model for Twitter Sentiment Analysis.
Dataset conatins train.csv and test.csv contain 29,530 and 16,130 tweets respectively provieded by Kaggle.
Some of the general library requirements for this project are:
- numpy
- nltk
- pandas
- scikit-learn
- regex
- tweepy
Libraries specific to some methods are:
- keras with TensorFlow backend for RNN(bidirectional LSTM)
- scikit-learn
- xgboost for XGBoost
- nltk for vader sentiment analysing.
- Naive Bayes
- K-neighbour
- Random Forest
- Logistic
- XG Boost
- SVM
- RNN(bidirectional LSTM)
- Vader Pre-trained model
- BERT
- ULMFiT