Achieving Dual Carbon Goals: A Cross-National Analysis Using Text Mining

Despite the extensive research on how news media portray climate change in both developed and developing countries, there has been disproportionately little attention to cross-national comparisons of policy priorities and carbon emission profiles in countries at different stages of carbon neutrality. This study addresses this gap by employing a data-driven text mining approach to examine media coverage of carbon emissions in four major global stakeholders that significantly influence climate politics: China, the U.S., the U.K., and Australia. Using natural language processing tools, the study identifies both convergent and divergent themes and frames across these four national carbon discourses, and reveals their priorities and approaches to carbon emission reduction. It further analyzes both generic and country-specific frames in the context of each country's sociopolitical realities. The cross-national perspective and text mining method in this study show the potential of data-driven approach in revealing geographic variations in addressing climate change.