AI-Based Modeling for Textual Data on Solar Policies in Smart Energy Applications

This study aims to examine sentiments and themes in deploying solar energy, after the recent enactment of the Clean Energy Act. It uses text on solar energy from public dockets and open access social media platforms to fathom mass opinion. It is crucial for policymakers / stakeholders in smart and renewable energy to address challenges of energy efficiency and equity. While we deal with solar energy, many claims here are valid for other sources such as offshore wind. We propose to harness the AI-based models of VADER, SentiWordNet and TextBlob for sentiment analysis, and Latent Dirichlet Allocation (LDA) for topic modeling, entailing NLP (natural language processing), to discover knowledge from the given text on prevalent attitudes concerns and endorsements. The approach dissects textual data, from assessing nuanced sentiment in social media to extracting major discussion themes. Numerical analysis on the modeled data with Pearson's correlation coefficient offers more insights. Findings reveal public reaction to solar energy policy, levels of awareness, mass acceptance, equity issues etc. This novel study underscores an interplay of solar policy, its mass perception, and renewable energy usage. It applies AI with a multi-modal holistic approach, mining textual data to help overcome the challenges of policy acceptance. It also aims to use AI to balance energy efficiency and equity, enhancing public engagement for transition to a fair, sustainable energy future for a smart planet.