Today, we live in a world of mis-information and fake news. The goal of this project is to detect fake news using machine learning classification models (Logistic Regression, Random Forest Classifier, Support Vector Machine and others). Fake news detector is crucial for companies and media to automatically predict whether circulating news is fake or not. I will analyze thousands of news text to detect if it is fake or not.
- Naive Bayes Classifier: 93.44%
- Decision Tree Classifier: 99.49%
- Support Vector Machine Classifier: 99.09%
- K-Nearest Neighbors (K-NN): 86.95%
- Logistic Regression Classifier: 98.49%
- Random Forest Classifier: 99.04%
- XGBoost Classifier: 99.60%
- LightGBM Classifier: 99.72%
- AdaBoost Classifier: 99.52%
In conclusion, the machine learning classification models performed well. We received accuracy rate more than 90% except K-Nearest Neighbors. Almost all of the models have closer accuracy score to each other. LightGBM Classifier gave the highest accuracy score (99.7%).