AI-Driven Framework for Evaluating Climate Misinformation and Data Quality on Social Media

In the digital age, climate change content on social media is frequently distorted by misinformation, driven by unrestricted content sharing and monetization incentives. This paper proposes a novel AI-based framework to evaluate the data quality of climate-related discourse across platforms like Twitter and YouTube. Data quality is defined using key dimensions of credibility, accuracy, relevance, and sentiment polarity, and a pipeline is developed using transformer-based NLP models, sentiment classifiers, and misinformation detection algorithms. The system processes user-generated content to detect sentiment drift, engagement patterns, and trustworthiness scores. Datasets were collected from three major platforms, encompassing over 1 million posts between 2018 and 2024. Evaluation metrics such as precision, recall, F1-score, and AUC were used to assess model performance. Results demonstrate a 9.2% improvement in misinformation filtering and 11.4% enhancement in content credibility detection compared to baseline models. These findings provide actionable insights for researchers, media outlets, and policymakers aiming to improve climate communication and reduce content-driven polarization on social platforms.