Information Technology for Detecting Fakes and Propaganda Based on Machine Learning and Sentiment Analysis

Abstract

This article provides a comprehensive study of modern approaches used to identify fakes and propaganda. Machine learning is emerging as a dynamic tool for pattern recognition and adaptation that facilitates real-time analysis. In addition, the article provides an analysis of propaganda based on emotional colouring, which reveals the differences between propaganda and non-propaganda. The average emotional value for propaganda news is 0.151 and for non-propaganda news is 0.116. The average degree of subjectivity for propaganda news is 0.365 and for non-propaganda news is 0.283. The average value of positive emotion for propaganda news is 0.087 and for non-propaganda news is 0.082. The average negative emotion for propaganda news is 0.064 and for non-propaganda news is 0.034. -The average value of the complex emotional colouring for propaganda news is 0.021, and for non-propaganda news - 0.010. Keywords – propaganda, fakes, NLP, natural language processing, disinformation detection, machine learning, multimodal analysis.