Computational Approaches and Message Effects Research (CAMER)

The Computational Approaches and Message Effects Research (CAMER) group, directed by Sijia Yang, studies persuasive messages as they are produced, promulgated, and processed in the broader digital informational environment. Our group is particularly interested in exploring how experimental, computational (e.g., automated multimodal content analysis, causal machine learning, web-based experiments), and community-engaged approaches can help advance our understanding of how persuasive messaging works as it intersects with psychological processes, social dynamics, and technological affordances, particularly in the contexts of public health and science communication.

Currently, we are focusing on the following lines of research:

  1. moralization and politicization of health/science issues and the implications for public health;
  2. visual persuasion and the feasibility of employing computer vision techniques and causal machine learning to predict and explain the persuasiveness of health-related messages (e.g., online advertisements of emerging tobacco and cannabis products, pictorial health warnings, multimodal health campaign messages); and
  3. human-AI interaction and the potential of using AI to improve health communication, particularly among underserved communities (e.g., vaccine promotion in rural areas, generative AI and health message design, AI-facilitated fact-checking of health information).

Faculty Leader: Sijia Yang

Recent News and Posts