We develop a novel and generic text-based measure to classify and evaluate greenhouse gas (GHG) disclosures. We construct the measure using collocation analysis of GHG-related words and regular expressions. Automated implementation achieved high concordance compared to manual investigations. We move beyond the “bag-of-words” approach in classifying voluminous nonfinancial corporate disclosure. We also outline a methodology that is manyfold scalable and makes replicability straightforward. Compared to past studies, we work with a significantly larger sample of 5,017 reports across 80 countries, thereby dealing with greater complexity and leading to better generalizability. We also contribute to the debate on whether nonfinancial disclosures exhibit accountability or are merely greenwashing. We find a negative trend in accountability worldwide, and firm-level accountability in GHG disclosures is not detectable in a country-level reduction of GHG emissions. Moreover, firms disclose significantly higher accountable information in a civil-law legal environment compared to those in a common-law legal environment.