IMDb Movie Review Sentiment Analysis

Overview

This project provides a simple web application for sentiment analysis of IMDb movie reviews using a pre-trained TensorFlow model. The application is built with Streamlit, allowing users to input a movie review and receive a sentiment prediction (Positive or Negative).

Features

• Input a movie review via a text area.
• Analyze the sentiment using a pre-trained TensorFlow model.
• Display the predicted sentiment (Positive or Negative).

Requirements

• Python 3.8+
• Streamlit
• TensorFlow

Installation

1. Clone the repository:

   git clone <repository_url>
   cd <repository_directory>

2. Install the required packages:

   pip install -r requirements.txt

3. Ensure the pre-trained model file (path_to_your_model.h5) is available and update the load_model function in dl_movie.py with the correct file path.

Usage

1. Run the Streamlit app:

   streamlit run dl_movie.py

2. Open the provided URL in your browser (typically http://localhost:8501).
3. Enter a movie review in the text area and click "Analyze Review" to see the sentiment prediction.

File Structure

• dl_movie.py: Main application script containing the Streamlit app and model logic.
• path_to_your_model.h5: Pre-trained TensorFlow model file (update path as needed).
• requirements.txt: List of required Python packages.

Notes

• The model file (path_to_your_model.h5) must be a valid TensorFlow model trained for binary sentiment classification.
• The predict_sentiment function assumes a binary classification threshold of 0.5.
• Ensure the model path in load_model is correctly set before running the app.