Using algorithms to identify social activism and climate skepticism in user-generated content on Twitter

Abstract

Climate change has become an issue of great relevance in society in recent years, and the data provided by the scientific community recommend acting as soon as possible and forcefully. Scientists, politicians, the media, and thanks to the new media, citizens and other social agents participate in the debate on this issue. Despite the data and general consensus in the scientific community, the climate change debate is highly polarized, with skeptical voices denying or questioning climate change and using social media to amplify the reach of their message. This can encourage misinformation and polarization. This study tries to identify the key indicators of social skepticism around climate change through the analysis of users’ social activism and behavioral patterns on Twitter. We analyze keywords, frequency, topics, and categories from a sample of 78,168 tweets. The results show, first, that there is an overlap of topics, with 24 of the 28 topics grouped in the intertopic distance map; second, that the size of the topics is relatively small and linked to specific events; and, third, that there is a significant political presence, especially from the United States. This work therefore contributes to the analysis of communication on Twitter about opinions against climate change.