Due to the influence of terrain and climate， the risk of highway slope disasters in Meizhou City is prominent. This study focuses on a 500-meter range on either side of the existing mainline highways in Meizhou， selecting eight evaluation factors—elevation， slope， curvature， lithology， NDVI， TWI， annual average rainfall， and maximum monthly rainfall—to construct a highway slope disaster susceptibility index evaluation system. Based on historical highway slope disaster data， a Bayesian network model is established to predict the susceptibility of highway slopes to disasters and further to analyze the distribution characteristics of landslide hazards under different rainfall scenarios. The conclusions are as follows： 1） The Bayesian network model for highway slope disaster susceptibility evaluation achieves an AUC of 0.832， indicating good reliability. Additionally， the SHAP values from the Bayesian network model show that lithology， slope， and maximum monthly rainfall are the three most influential factors affecting highway slope disasters in Meizhou City. 2） Considering three rainfall scenarios （1-in-10， 1-in-50， and 1-in-100-year events）， the areas of extremely high-risk regions gradually increased， accounting for 13%， 19%， and 22%， respectively. 3） Based on web scraping tools to retrieve social media data， all historical highway slope disaster cases in Meizhou are located in regions classified as high and extremely high hazard levels. The findings of this study provide a valuable reference for the prevention and control of highway slope disasters in Meizhou City.