https://github.com/abhiiiman/twitter_sentiment_analysis
Predict the sentiments of the Twitter tweets in a go using NLP techniques and Logistic Regresion Model.
https://github.com/abhiiiman/twitter_sentiment_analysis
deployed nlp nlp-machine-learning render sentiment streamlit twitter twitter-sentiment-analysis
Last synced: about 1 month ago
JSON representation
Predict the sentiments of the Twitter tweets in a go using NLP techniques and Logistic Regresion Model.
- Host: GitHub
- URL: https://github.com/abhiiiman/twitter_sentiment_analysis
- Owner: abhiiiman
- Created: 2024-06-19T15:57:08.000Z (about 2 years ago)
- Default Branch: master
- Last Pushed: 2024-06-19T16:33:12.000Z (about 2 years ago)
- Last Synced: 2025-01-12T18:51:53.860Z (over 1 year ago)
- Topics: deployed, nlp, nlp-machine-learning, render, sentiment, streamlit, twitter, twitter-sentiment-analysis
- Language: Jupyter Notebook
- Homepage: https://twitter-sentiment-analysis-e1b1.onrender.com/
- Size: 9.18 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Twitter Sentiment Analysis đĻđâšī¸
### This project leverages _Natural Language Processing_ __(NLP)__ and _Logistic Regression_ to classify the sentiment of tweets as either `positive` or `negative`. The model achieved an accuracy of `82%`. Below you'll find detailed instructions on how to set up and run this project locally, as well as how to use the deployed `Streamlit` app.
# Project Structure
## Setup Instructions
1. **Clone the Repository**
```html
git clone https://github.com/abhiiiman/Twitter_Sentiment_Analysis.git
```
```html
cd Twitter_Sentiment_Analysis
```
2. **Create a Virtual Environment**
```html
python -m venv venv
```
- Mac Users
```html
source venv/bin/activate
```
- Windows Users
```html
venv\Scripts\activate
```
3. **Install Dependencies**
```html
pip install -r requirements.txt
```
4. **Download NLTK Data**
- In a Python shell, run:
```python
import nltk
nltk.download('stopwords')
nltk.download('punkt')
```
5. **Download the Dataset from here**
[Download the Dataset](https://www.kaggle.com/datasets/kazanova/sentiment140)
6. **Run the Streamlit App**
```html
streamlit run app.py
```
# Using the Deployed Streamlit App
1. Navigate to the Streamlit App [Click Here](https://twitter-sentiment-analysis-e1b1.onrender.com/)
2. Enter Tweet Content
3. Predict Sentiment
4. Screenshots
- Negative Tweet
- Positive Tweet
# Don't forget to give it a Star!
## _If you loved this project, give it a_ â _on GitHub! It would make my codebase as happy as a positive tweet_ đ.