The "Cyberbullying Tweet Detection" project looks into the world of machine learning to tackle the essential problem of cyberbullying detection in online communication. This project focuses on the creation and implementation of cutting-edge machine learning models to automatically recognize and categorize tweet content containing cyberbullying.
The backend of the application is built using Flask, a lightweight WSGI web application framework in Python. It exposes endpoints to receive text inputs, process them through pre-trained machine learning models, and return predictions on whether the input text contains cyberbullying content.
-
Clone the Repository
git clone https://github.com/santhoshprabhuV2003/cyberbullying-tweet-detection.git cd backend -
Set Up Virtual Environment
python -m venv venv venv/Scripts/activate # On Windows source venv/bin/activate # On macOS/Linux
-
Install Dependencies
pip install -r requirements.txt
-
Run the Flask App
python app.py
The Flask app will start running locally at http://localhost:5000. You can access the /predict endpoint by a post request with text as body of the request.
Else you can build a docker image using the Dockerfile and run the flask application as a container.
The frontend provides a user-friendly interface for interacting with the cyberbullying detection system. It is built using React and includes three main pages: Home, Models, and Dataset.
-
Home: Provides an overview of the project, explains how users can input text to predict cyberbullying, and displays the results.
-
Models: Discusses the machine learning algorithms used in building the models, including Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest (RF).
-
Dataset: Provides insights into the dataset used for training the models, including its sources and composition.
-
Clone the Repository
git clone https://github.com/santhoshprabhuV2003/cyberbullying-tweet-detection.git cd frontend/cyberbullying-tweet-detection -
Install Dependencies
npm install
-
Run the React App
npm start
The React app will start running locally at http://localhost:3000.
https://santhoshprabhuv2003.github.io/cyberbullying-tweet-detection/
The machine learning models developed in the "Cyberbullying Tweet Detection" project have achieved an impressive accuracy rate of 83% in effectively identifying and categorizing cyberbullying content in English language tweets. Please note that while the system is highly accurate, it may not detect all instances of cyberbullying.