The aim of this project is to provide users a real time movie review ,based on the latest tweets or trends. This project has been developed as a POC.
-
A brief explaination about the methodlogy used:-
- The model has been trained on the IMDB dataset available on Kaggle.
- The model uses Twitter API i.e. tweepy to fetch tweets that mentions the given movie/topic.
- After the tweets has been fetched and stored, the data is then pre-processed for the model.
- The model then predicts the outcome as categories i.e positive or negative ,then the percenatge of people having either positive or negative review is calcuated.
-
Task performed:- The classical Machine Learning task like data exploration,feature engineering,model buiding, model testing,Hyperparameters tuning etc.
-
Deployment:- The model has been deployed using Heroku Cloud application platform where Github is used for version control.
-
Model:- Model used here is Logistic Regression.
-
Accuracy:- The model has a prediction accuracy greater than 88.00%.
-
Demo Video:- https://user-images.githubusercontent.com/90147069/139523670-0ef213db-0949-4f28-b990-6fa9c8647f6c.mp4