Causal Sentiment-Driven Reinforcement Learning Framework for Adaptive Solar Energy Policy Design

The global energy transition demands not only technological innovation but also adaptive policy mechanisms that respond to shifting public sentiment and socio economic conditions. This paper presents a novel sentiment aware reinforcement learning framework for solar energy policy optimization that integrates transformer based natural language processing, structural causal modeling, and deep reinforcement learning. First, public sentiment is extracted from diverse unstructured textual sources including social media and global news using RoBERTa, a transformer model fine tuned on energy related discourse. These sentiment scores are then incorporated into a Structural Causal Model (SCM) to estimate their causal impact on solar adoption, adjusting for key confounders such as GDP, electricity pricing, and subsidy levels. The inferred causal insights are used to guide a Proximal Policy Optimization (PPO) reinforcement learning agent that recommends adaptive policy actions including subsidy changes, awareness campaigns, and regulatory shifts aimed at maximizing long term adoption and minimizing economic cost. The framework is evaluated across multiple geographic regions and policy scenarios using real world economic and social data streams. Results demonstrate that sentiment-driven policies significantly outperform static or heuristic baselines in both adoption rate and fiscal efficiency. The inclusion of explainability modules, such as SHAP values and policy entropy metrics, enhances model transparency and stakeholder trust. This end-to-end system not only captures the complex, dynamic interaction between public perception and policy response but also offers a scalable, interpretable, and real-time decision support tool for energy governance. The proposed methodology has broader implications for AI-driven policymaking across climate, mobility, and public health domains.