Detecting Religious Language in Climate Discourse

TL;DR

This study compares rule-based and LLM methods for detecting religious language in climate discourse, revealing methodological challenges and highlighting the persistence of sacred language in secular environmental texts.

Contribution

It introduces a dual approach combining a hierarchical rule-based model and LLMs to analyze religious language in climate-related texts, advancing digital religious studies methods.

Findings

Rule-based method labels more religious sentences than LLMs

Detection methods differ in identifying explicit vs. implicit religious language

Highlights challenges in computationally defining religious language

Abstract

Religious language continues to permeate contemporary discourse, even in ostensibly secular domains such as environmental activism and climate change debates. This paper investigates how explicit and implicit forms of religious language appear in climate-related texts produced by secular and religious nongovernmental organizations (NGOs). We introduce a dual methodological approach: a rule-based model using a hierarchical tree of religious terms derived from ecotheology literature, and large language models (LLMs) operating in a zero-shot setting. Using a dataset of more than 880,000 sentences, we compare how these methods detect religious language and analyze points of agreement and divergence. The results show that the rule-based method consistently labels more sentences as religious than LLMs. These findings highlight not only the methodological challenges of computationally detecting religious language but also the broader tension over whether religious language should be defined by vocabulary alone or by contextual meaning. This study contributes to digital methods in religious studies by demonstrating both the potential and the limitations of approaches for analyzing how the sacred persists in climate discourse.