https://github.com/akshadk7/lstm_sentiment_analysis
A Bidirectional LSTM Approach to the Twitter Sentiment Analysis Model
https://github.com/akshadk7/lstm_sentiment_analysis
Last synced: 2 months ago
JSON representation
A Bidirectional LSTM Approach to the Twitter Sentiment Analysis Model
- Host: GitHub
- URL: https://github.com/akshadk7/lstm_sentiment_analysis
- Owner: AkshadK7
- Created: 2021-10-27T14:11:41.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2021-10-27T14:18:31.000Z (almost 4 years ago)
- Last Synced: 2024-07-25T12:11:10.099Z (about 1 year ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 8.1 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# LSTM Sentiment Analysis
A Bidirectional LSTM Approach to Twitter Sentiment Analysis.
## Overview
This project implements a Bidirectional Long Short-Term Memory (Bi-LSTM) model to perform sentiment analysis on Twitter data. The model is designed to classify tweets into positive or negative sentiments, enhancing the understanding of public opinion on various topics.
## Repository Contents
- `Bi_LSTM_Sentiment_Analysis.ipynb`: Jupyter Notebook containing the data preprocessing steps, model architecture, training process, and evaluation metrics.
- `dataset.zip`: Compressed file containing the dataset used for training and testing the model.
- `README.md`: Project documentation.
## Requirements
- Python 3.x
- Jupyter Notebook
- TensorFlow
- Pandas
- NumPy
- Scikit-learn
- NLTK (Natural Language Toolkit)
## Setup Instructions
1. **Clone the Repository**:
```bash
git clone https://github.com/AkshadK7/LSTM_Sentiment_Analysis.git
cd LSTM_Sentiment_Analysis
```
2. **Install Dependencies**:
It's recommended to use a virtual environment to manage dependencies.
```bash
pip install -r requirements.txt
```
3. **Extract the Dataset**:
Unzip the `dataset.zip` file to access the dataset.
4. **Run the Jupyter Notebook**:
```bash
jupyter notebook Bi_LSTM_Sentiment_Analysis.ipynb
```
## Usage
- Open the `Bi_LSTM_Sentiment_Analysis.ipynb` notebook.
- Follow the steps outlined to preprocess the data, train the Bi-LSTM model, and evaluate its performance.
- Modify the notebook as needed to experiment with different model architectures or parameters.
## Results
The model's performance metrics and visualizations of the predictions versus actual sentiments are provided in the notebook. These insights can help in understanding the model's accuracy and areas for improvement.
## License
This project is licensed under the MIT License. See the [LICENSE](https://github.com/AkshadK7/LSTM_Sentiment_Analysis/blob/main/LICENSE) file for details.
## Acknowledgements
Special thanks to the contributors of the datasets and the open-source community for providing tools and libraries that made this project possible.
```
*Note: Ensure that the `requirements.txt` file includes all necessary dependencies for the project. If it doesn't exist, you may need to create it by listing the required packages.*