This project is a simple implementation of sentiment analysis on the popular IMDb movie review dataset. It uses Natural Language Processing (NLP) techniques to classify movie reviews as positive or negative. It also includes wordclouds of positive and negative reviews to visualize the common words in each category.
The dataset consists of 50,000 movie reviews, with 25,000 reviews for training and 25,000 for testing. Each review is labeled as either positive or negative. The model is trained on the training set and tested on the testing set to evaluate its accuracy.
To run this project, you will need the following libraries:
- NumPy
- Pandas
- Matplotlib
- Keras
- TensorFLow
- WordCloud
You can install the required packages using the following command:
pip install pandas
- Clone this repository to your local machine.
- Open a terminal in the project directory.
- Run Jupyter Notebook using the following command:
jupyter notebook
- Open the IMDB_Sentiment_Analysis.ipynb notebook.
- Follow the instructions in the notebook to run the code and train the model.
The final accuracy achieved by the model was 86,46% on the testing set. The notebook contains detailed explanations of the code and the techniques used.