Pipeline for modeling causal beliefs from natural language

Causal reasoning is a core cognitive function and is central to how people learn and update their beliefs. Causal information is also central to how people represent and use language. Natural Language Processing algorithms that detect people's causal representations can illuminate the considerations shaping their beliefs and reasoning. We present a causal language analysis pipeline that leverages a Large Language Model to identify causal claims in natural language documents, and aggregates claims across a corpus to produce a causal claim network. The pipeline then applies a clustering algorithm that groups causal claims according to their semantic topics. We demonstrate the pipeline by modeling causal belief systems surrounding the Covid-19 vaccine from tweets.