In a recent study published in the journal Humanities and Social Sciences Communications , researchers investigated the role of sentiment and emotional features in detecting fake news by comparing emotions associated with fake and real news. Their findings indicate that integrating emotional features, particularly negative emotions, into machine learning models significantly enhances the accuracy and reliability of fake news detection on social media platforms. Study: Emotions unveiled: detecting COVID-19 fake news on social media .
Image Credit: voyata / Shutterstock It is well established that social media significantly impacts various aspects of human life, offering benefits like connectivity and information sharing and presenting dangers such as spreading fake news. The research highlighted that fake news undermines public trust, democracy, and economic stability. Notable incidents during the 2016 United States presidential election and the coronavirus disease 2019 (COVID-19) pandemic illustrate its serious consequences.
Although previous studies examined cognitive biases and the structural aspects of social media that facilitate the spread of fake news, as well as various machine learning techniques for detecting it, there was a notable gap in understanding the role of emotions in fake news detection. This study aimed to explore how emotional features, particularly negative emotions, could enhance the accuracy of machine learning models in detecting fake news. Researcher.