This research paper addresses the impact of the positive or negative polarity of the presidential messages contained in the stenographic version of the daily conferences issued by the president of Mexico, obtained by means of semantic and machine learning text mining techniques, on the performance of the Mexican Stock Exchange’s Price and Quotations Index (Índice de Precios y Cotizaciones-IPC). Our results provide evidence of the existence of a negative and significant relationship of the polarity of presidential messages with IPC performance, i.e., as the positive polarity of messages increases, IPC performance decreases.