Sentiment-Explorer-Using-Simple-RNN

This project demonstrates how to use a Simple Recurrent Neural Network (RNN) to classify IMDb movie reviews as positive or negative.

Table of Contents

• Introduction
• Dataset
• Model Architecture
• Prerequisites
• Steps to run in VS code

Introduction

Sentiment analysis is a common task in natural language processing (NLP) that involves determining the emotional tone behind a text. In this project, we use the IMDb dataset, a collection of movie reviews labeled as positive or negative, to train and evaluate a Simple RNN model.

Dataset

The dataset is part of the TensorFlow/Keras library and can be directly loaded using: python

     from tensorflow.keras.datasets import imdb

Model Architecture

The Simple RNN model consists of the following layers:

1. Embedding Layer: Converts word indices to dense vectors of fixed size.
2. Simple RNN Layer: Processes sequences of embeddings to capture temporal dependencies.
3. Dense Layer: Fully connected layer with a single neuron and sigmoid activation for binary classification.

Model Summary

Prerequisites

• Python 3.8+
• TensorFlow 2.0+
• NumPy
• Matplotlib (optional, for visualization)

Run the code using steps -

1. Clone the repository

 git clone <url_of_repository>

2. Select the kernel and run all the files.
3. Run main.py using commond

   streamlit run main.py

4. Enter the movie review & classify it as positive or negative.

Web app

---

---