Exploring the Role of Language in Public Perception of Environmental Health and Exposure Risks Using EEG

Understanding public perception of environmental health and exposure risks is essential for effective communication and policy-making. Traditional methods, such as surveys and retrospective analyses, often fail to capture real-time cognitive and emotional responses. To address these limitations, this study introduces the Cognitive-Linguistic Integration Framework (CLIF), which integrates linguistic modeling with EEG-based cognitive state analysis. By leveraging deep learning and knowledge-augmented reasoning, CLIF effectively deciphers how language shapes perception and decision-making. Experimental results demonstrate the framework’s ability to enhance semantic alignment, improve adaptability in real-time contexts, and outperform existing methods in capturing neural responses to environmental risk communication. These findings provide actionable insights for designing more effective public engagement strategies and evidence-based policy recommendations. Experimental results on EEG datasets, including EEGEyeNet and CWL EEG/fMRI, demonstrate the model’s efficacy in capturing neural responses to linguistic framing, achieving superior semantic alignment, real-time adaptability, and improved accuracy in cognitive state modeling compared to traditional approaches.