sweta-kesur-nlp-playground / nlp-play1-movie-reviews

Real time application of Sentiment Analysis on Movie Reviews. A Machine Learning Flask App hosted on Heroku and created on Google Colab. https://swetakesurnlp-playground.herokuapp.com

My First NLP Play - Sentiment Analysis on Movie Reviews

Demo: https://swetakesurnlp-playground.herokuapp.com

How it Works?

1. Enter a movie review inside the white text box as shown in the image.
2. Click PREDICT button to see the results of sentiment analysis of your review.
3. Check the results of your review whether it is a POSITIVE or a NEGATIVE review.

Dataset Information

I have used 50K Movie review dataset from Kaggle. You can get it from this link. This is a dataset for binary sentiment classification containing substantially more data than previous benchmark datasets. We provide a set of 25,000 highly polar movie reviews for training and 25,000 for testing. So, predict the number of positive and negative reviews using either classification or deep learning algorithms.

Requirements

There are some library requirements for the project. For further details about the version of these libraries, please check requirements.txt file.

• numpy
• scikit-learn
• scipy
• nltk
• gunicorn
• beautifulsoup4
• bs4
• Flask
• flask-ngrok
• itsdangerous
• Jinja2
• joblib
• MarkupSafe
• matplotlib
• pandas
• Werkzeug

Note: It is recommended to use Google Colab to run this project.

Contact

Feel free to contact me on any of my social media accounts if you encounter any difficulties in running this project.

1. Linkedin
2. Twitter
3. Facebook
4. Quora
5. Email