Samuel and Colleagues Examine the Rise of AI Phobia

Contemporary public discourse surrounding artificial intelligence (AI) often exhibits a disproportionate level of fear and confusion relative to AI’s factually documented capabilities and implications. This study examines how the systematic use of alarmist and fear-inducing language by news media outlets contributes to negative public perceptions of AI. This study analyzed nearly 70,000 AI-related news headlines using natural language processing (NLP) methods, machine learning (ML) algorithms, and large language models (LLMs) to identify dominant themes and sentiment patterns. The theoretical framework draws on existing literature that posits the power of fear-inducing headlines to influence public perception and behavior, even when such headlines represent a relatively small proportion of total coverage. The methods used include classical and state-of-the-art NLP techniques such as word frequency analysis, sentiment analysis, emotion classification, topic modeling, and thematic evaluations by human experts. Topic modeling and fear sentiment classification were performed using BERT, LLaMA, and Mistral, in conjunction with supervised ML techniques. The findings show a consistently notable presence of emotionally negative and fear-laden language in AI news coverage. This portrayal of AI as being dangerous to humans, or other negative views such as AI being an existential threat to humanity, has a profound impact on public perception, and the resulting AI phobia and confusion lead to behavioral resistance toward AI, and are inherently detrimental to the science of AI. Furthermore, this can also have an adverse impact on AI policies and regulations, leading to a stunted growth environment for AI. This study concludes with the articulation of implications and recommendations to counter fear-driven narratives, and suggests ways to improve public understanding of AI through responsible news media coverage, broad AI education, democratization of AI resources, and the drawing of clear distinctions between AI as a science versus commercial AI applications, to promote enhanced fact-based mass engagement with AI, while preserving human dignity and agency.