Approaches for Improving the Performance of Fake News Detection in Bangla: Imbalance Handling and Model Stacking

Abstract

Imbalanced datasets can lead to biasness into the detection of fake news. In this work, we present several strategies for resolving the imbalance issue for fake news detection in Bangla with a comparative assessment of proposed methodologies. Additionally, we propose a technique for improving performance even when the dataset is imbalanced. We applied our proposed approaches to BanFakeNews [4], a dataset developed for the purpose of detecting fake news in Bangla comprising of 50K instances but is significantly skewed, with 97% of majority instances. We obtained a 93.1% F1-score using data manipulation manipulation techniques such as SMOTE, and a 79.1% F1-score using without data manipulation approaches such as Stacked Generalization. Without implementing these techniques, the F1-score would have been 67.6% for baseline models. We see this work as an important step towards paving the way of fake news detection in Bangla. By implementing these strategies the obstacles of imbalanced dataset can be removed and improvement in the performance can be achieved.