Using the U.S. Renewable Fuel Standard (RFS) as a case study, this chapter contrasts the growing potential of big data research methodologies with the limitations of conventional policy analysis methods. Established via amendments to the Clean Air Act in the early 2000s, the RFS was designed to increase U.S. energy independence and reduce greenhouse gas emissions caused by the combustion of transportation fuels. More than 20 years later, the RFS remains the subject of significant discourse and debate amongst legislators, federal agencies, and stakeholder groups. Through an analysis of RFS-related social media posts and associated metadata collected from Twitter (now known as “X”), the authors utilize machine learning and content analysis to assess public discourse and stakeholder perspectives. The research explores the intersection of policy, politics, and public sentiment using the Multiple Streams Framework to reveal the complexities of advocacy, opposition, and the framing of the RFS in public debates. The results provide support for both the significance of machine learning methods and the relevance of Multiple Streams as a theoretical framework. Legislator advocacy or opposition is strongly correlated with the characteristics of their district, reflecting the interests and livelihoods of the voters who elect them to office.