Impactful messaging: Elite sentiment in Chinese new energy vehicle vs machine learning perspective

Abstract

Elite messaging is sensitive to framing decisions and shaping public sentiment. This study examines the influence of elite sentiment on the pricing of the stock index of China's new energy vehicles (NEVs). To construct elite sentiment indexes for China's NEVs, data from a highly active online elite forum were collected and a series of machine learning models were utilized to generate predictions. The results demonstrate that the elite sentiment index has a pronounced predictive impact on stock index prices. Furthermore, incorporating the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method can further enhance the baseline model's predictive ability.