Celebrity deaths: On the automatic classification of unintentional fake news

Abstract

This study addresses the growing problem of information disorder, particularly in the context of celebrity death announcements. As the rapid spread of disinformation becomes a critical societal issue, particularly through mass media and social media, it is essential to understand the mechanisms behind this phenomenon. The research employs an interdisciplinary approach, integrating computational, linguistic, sociological, and journalistic perspectives to analyze the characteristics of unintentional fake news. Using machine learning classification techniques, we seek to differentiate between unintentional fake news, real news that debunks these false claims, and actual news. The findings reveal significant linguistic features that contribute to the classification process. However, although there are models capable of classifying certain types of news, none can accurately classify all the types considered, highlighting the complexities involved in distinguishing between accurate information, misinformation, and disinformation. This work not only sheds light on the nature of unintentional fake news but also emphasizes the need to improve verification processes in journalism to combat the viral spread of false information. Ultimately, the study calls for further research into the implications of these findings for media practices and the role of technology in addressing the challenges of information disorder in contemporary society.