Predicting government microblog comment popularity: insights from diffusion of innovations.

Abstract

Government microblog comments (GMCs) play a crucial role in facilitating public opinion and governmental communication. This study explores the prediction of GMC popularity using machine learning methods, emphasizing an innovative approach that integrates diffusion of innovations theory with a hierarchical feature framework. Along with an interpretable tabular learning algorithm, the experiments demonstrate the effectiveness of this feature-framework-based method, which outperforms pretrained large language models in predicting social media comment popularity. This approach illustrates the value of combining theory-driven feature engineering with cutting-edge machine learning to predict social media engagement. Additionally, the results provide actionable insights for government agencies to monitor public opinion trends and enhance decision-making processes.