Umutoniwasepie/Kinyarwanda_Hatespeech_Detection

# Kinyarwanda Hate Speech Detection App A machine learning-powered app that detects **hate**, **offensive**, or **normal** speech in **Kinyarwanda** social media text using logistic regression. Also includes a **Chrome extension** (Developer Mode) for real-time classification. --- ## 🚀 Features - ✅ Detects `hate`, `sarcasm`, or `normal` content in Kinyarwanda - 🧠 Trained with Logistic Regression + TF-IDF - 📊 Balanced dataset for fair classification - 🌐 Web interface for testing input text - 🧩 Chrome extension for live web integration --- ## 📁 Project Structure ``` project/ │ ├── app.py #Flask app |── README.md |── Procfile ├── requirements.txt ├── . |── static/css | ├── dashboard.css | ├── index.css | ├── login.css | ├── register.css | ├── moderator_dashboard.css | ├── verify.css | ├── forgot_password.css | ├── reset_password.css ├── templates/ | ├── dashboard.html | ├── index.html | ├── login.html | ├── register.html | ├── moderator_dashboard.html | ├── verify.html | ├── forgot_password.html | ├── reset_password.html ├── model/ │ ├── hate_speech_model.ipynb # Model Notebook | ├── kinyarwanda_hatespeech_noisy.csv | ├── final_dataset.tsv | ├── label_encoder.pkl | ├── model.pkl # Trained logistic regression model | ├── tfidf.pkl # TF-IDF vectorizer used during training ├── RHD_extension/ # Chrome extension source files │ ├── manifest.json │ ├── popup.html │ ├── popup.js │ ├── icon.png │ └── content.js │ ├── background.js ├── screenshots/ ``` --- ## 🛠️ Installation (Web App) ### Step 1: Clone the Repository ```bash git clone github.com cd kinyarwanda_Hatespeech_Detection ``` ### Step 2: Create Virtual Environment ```bash python -m venv venv venv\Scripts\activate ``` ### Step 3: Install Dependencies ```bash pip install -r requirements.txt ``` ### Step 4 (Optional): Train the Model Open the notebook: ```bash jup …