The primary goal of this project is to build a sentiment analysis model that can predict the sentiment of a given review (positive or negative).
This project involves sentiment analysis on Amazon Alexa reviews using deep learning and traditional machine learning techniques. The objective is to classify the reviews as either positive or negative based on their content. The dataset consists of 36 lakh train data points used for training and validation, and 4 lakh test data points for evaluation.
Clone the repository:
git clone https://github.com/MPoojithavigneswari/Sentiment-Analysis.git
cd Sentiment-Analysis
Install the dependencies:
pip install -r requirements.txt
Run the Streamlit app:
streamlit run streamlit_app.py
This generates a link and opens it in your web browser. Enter the any review to get its predicted sentiment.
The dataset isw large and consists of Amazon Alexa product reviews, which include the review text and the corresponding sentiment label (positive or negative). Click here to download the dataset.
The Streamlit app is deployed and hosted at Sentiment Analysis Web App.
The Logistic Rgrssion model achieved an accuracy of 87.5% on the test set. The Streamlit app provides a user-friendly interface for predicting the sentiment of new reviews.
Contributions are welcome! Please fork the repository and submit a pull request for any improvements or bug fixes.