Automatic detection of manipulated Bangla news: A new knowledge-driven approach

Abstract

In recent years, dissemination of misleading news has become easier than ever due to the simplicity of creating and distributing news content on online media platforms. Misleading news detection has become a global topic of interest due to its significant impact on society, economics, and politics. Automatic detection of the veracity of news remains challenging because of its diversity and close resemblance with true events. In many languages, fake news detection has been studied from different perspectives. However, in Bangla, existing endeavors on fake news detection generally relied on linguistic style analysis and latent representation-based machine learning and deep learning models. These models primarily rely on manually labeled annotations. To address these challenges, we proposed a knowledge-based Bangla fake news detection model that does not require model training. In our proposed manipulation detection approach, a news article is automatically labeled as fake or authentic based on an authenticity score that relies on the consistency of knowledge and semantics, underlying sentiment, and credibility of the news source. We also propose a consistent and context-aware manipulated news generation technique to facilitate the detection of partially manipulated Bangla news. We found the proposed model to be a reliable one for the detection of both fake news and partially manipulated news. We also developed a dataset that is balanced according to the number of authentic and fake news for the detection of Bangla fake news, where news items are collected from multiple domains and various news sources. The experimental evaluation of our proposed knowledge-driven approach on the developed dataset has shown 97.08% accuracy for only fake news detection.