https://github.com/arindal1/sentiment-analysis-tf-keras

A python script for YouTube sentiment analysis using a Neural Network with TensorFlow and Keras.
https://github.com/arindal1/sentiment-analysis-tf-keras

keras machine-learning sentiment-analysis tensorflow youtube

Last synced: 3 days ago
JSON representation

A python script for YouTube sentiment analysis using a Neural Network with TensorFlow and Keras.

• Host: GitHub
• URL: https://github.com/arindal1/sentiment-analysis-tf-keras
• Owner: arindal1
• Created: 2023-10-16T18:22:51.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2023-10-16T19:10:32.000Z (about 1 year ago)
• Last Synced: 2023-10-17T08:23:06.128Z (about 1 year ago)
• Topics: keras, machine-learning, sentiment-analysis, tensorflow, youtube
• Language: Python
• Homepage:
• Size: 1.69 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        

# Sentiment Analysis with TensorFlow and Keras

This project demonstrates sentiment analysis using a neural network built with TensorFlow and Keras. The model is trained to classify text into three sentiment categories: negative, neutral, and positive.

## Introduction

Sentiment analysis, also known as opinion mining, involves analyzing and understanding the sentiment expressed in a piece of text. This project employs a neural network to predict the sentiment of input text.

## Installation

To set up and run this project, follow these steps:

1. Clone the repository:

   ```bash

   git clone 

   cd 

   ```

2. Install the necessary dependencies:

## Usage

- **Preprocessing**: The text data is preprocessed and tokenized using TensorFlow's Tokenizer. The sequences are padded to a fixed length for consistency.

- **Model**: A neural network model is defined using Keras, with an Embedding layer, GlobalAveragePooling1D, and Dense layers. The model is compiled and trained on the provided dataset.

- **Evaluation**: The model is evaluated on a test dataset to measure its performance.

- **Interactive Prediction**: Users can interactively input a sentence for sentiment analysis, and the trained model predicts the sentiment of the input.

## Model Training

- If the saved model exists, it is loaded.

- If not, a new model is trained using the provided dataset and saved for future use.

## Interactive Prediction

To predict sentiment for a custom input, run the provided script and follow the prompts.

```bash

python predict.py

```