M1urray/Hate-Speech-For-Swahili

# Swahili Hate Speech Detection System This project aims to build a machine learning model that can detect hate speech in Swahili text. The project is motivated by the need to address hate speech, which is a pervasive problem in online platforms and can cause harm to individuals and society. ## Dataset The project uses a publicly available dataset that contains Swahili text and is labeled for hate speech. The dataset contains about 5,000 tweets, and each tweet is labeled as either hate speech or not hate speech. The dataset was collected by researchers from the University of Dar es Salaam, Tanzania, and is available for research purposes. ## Model The project uses a supervised learning approach to train a machine learning model to detect hate speech in Swahili text. The model uses natural language processing techniques to preprocess the text and extract features that are fed into a machine learning algorithm. The project uses the following machine learning algorithms: - Logistic Regression - Naive Bayes - Support Vector Machines The project uses cross-validation to evaluate the performance of the models and select the best-performing algorithm. ## Requirements The project requires the following dependencies: - Python 3 - Scikit-learn - Pandas - Numpy - NLTK ## Usage To use the Swahili hate speech detection system, follow these steps: 1. Clone the repository to your local machine. 2. Install the dependencies listed in the requirements.txt file. 3. Run the app.py to get the web UI and enter your text and click on predict. ## License The project is licensed under the MIT License, which allows for the free use, modification, and distribution of the software for any purpose, provided that the original copyright notice and disclaimer are included. ## Credits The project was developed by Robert Kamau Njonjo and Fiston Alvin.The project uses the Scikit-learn, Pandas, Numpy, and NLTK Python libraries.