Mass hysteria, also known as mass psychogenic illness is referred to as a quick outbreak of fear, anxiety, or unreasonable behavior in many people at once, especially during an epidemic. The COVID-19 pandemic triggered a global climate of fear, uncertainty, exacerbated by a significant surge in misinformation. Forecasting and controlling such circumstances help reduce the effects and enhance public health measures. This research focuses on using machine learning (ML) to predict and understand mass hysteria in pandemic scenarios that may occur in future. The researchers analyze and observe large datasets, for example, social media posts, search engine data, health statistics, and news trends to identify patterns that lead to collective panic with techniques like natural language processing (NLP), time-series forecasting, and sentiment analysis which are used to spot early warning signs. It also monitors how hysteria develops over time to control it in the future. NLP techniques can analyze emotions and concerns expressed in text. The study also examines how misinformation, social factors, and demographic variables contribute to mass hysteria. This work combines ML models with behavioral and public health research to provide insights that can help policymakers, health organizations, and media platforms take action to reduce panic and build trust during future crises. This research thus underlines the potential of ML frameworks in solving the psychological and social challenges of pandemics, but it also puts across that preparation for, and management of a global emergency are very much needed in working across disciplines.
Sheikh et al. (Wed,) studied this question.