Research on Framework for and Strategies of Green Energy Consumption Based on Unsupervised Machine Learning

Documentary videos on green energy consumption are widely distributed via platforms such as YouTube, yet the verbal framing strategies embedded in their subtitle transcripts remain systematically understudied. This study applies the Analysis of Topic Model Networks (ATMN)—an unsupervised machine learning approach combining LDA topic modeling, semantic network analysis, and hierarchical clustering—to subtitle transcripts extracted from 60 YouTube green energy consumption documentaries. Three distinct framing communities are identified: (1) the Technological Supply Frame, which foregrounds zero-carbon resources, renewable generation, smart grid systems, and AI-enabled energy management as the technical foundation of decarbonization; (2) the Socioeconomic Transition Frame, the most thematically expansive, which positions the energy transition simultaneously as an economic opportunity, a behavioral imperative, and a systemic industrial transformation spanning green investment, end-use substitution, industrial decarbonization, and green mobility; and (3) the Ecological Governance Frame, which integrates ecological co-benefits with international climate commitments to construct the transition as a globally mandated planetary responsibility. Together, these frames reveal a richer and more multi-dimensional verbal framing landscape than previously documented in the green energy communication literature, extending beyond techno-optimism or environmentalism to encompass financial, governance, and behavioral dimensions within a single integrated corpus. The identified framing strategies offer actionable guidance for policymakers, energy enterprises, and media producers seeking to accelerate green energy consumption transition through targeted, evidence-based video communication.