The Climate Change Debate and Natural Language Processing

Manfred Stede, Ronny Patz

Abstract: The debate around climate change (CC)—its extent, its causes, and the necessary re- sponses—is intense and of global importance. Yet, in the natural language processing (NLP) community, this domain has so far received little attention. In contrast, it is of enor- mous prominence in various social science disciplines, and some of that work follows the ”text-as-data” paradigm, seeking to em- ploy quantitative methods for analyzing large amounts of CC-related text. Other research is qualitative in nature and studies details, nu- ances, actors, and motivations within CC dis- courses. Coming from both NLP and Po- litical Science, and reviewing key works in both disciplines, we discuss how social sci- ence approaches to CC debates can inform advances in text-mining/NLP, and how, in re- turn, NLP can support policy-makers and ac- tivists in making sense of large-scale and com- plex CC discourses across multiple genres, channels, topics, and communities. This is paramount for their ability to make rapid and meaningful impact on the discourse, and for shaping the necessary policy change.