Infodemics are the rapid spread of false or misleading information related to public health emergencies, often through digital platforms. They can cause confusion, fear, and even harm to public health. This study investigates the application of sentiment analysis for infodemic management during disease outbreaks. Leveraging the Extended Parallel Process Model (EPPM) of risk communication, the research aims to categorize rumors based on their perceived threat level (high, medium, or low). Machine learning is employed to analyze infodemic text data collected from two Nigerian states (Oyo and Bauchi) to assess threat appraisal according to the EPPM model. The findings can inform targeted interventions for effective infodemic management before, during, and after outbreak of diseases.