Table of Contents
Fetching ...

Detecting Religious Language in Climate Discourse

Evy Beijen, Pien Pieterse, Yusuf Çelik, Willem Th. van Peursen, Sandjai Bhulai, Meike Morren

TL;DR

This study addresses how religious language manifests within climate discourse by comparing a rule-based hierarchical tree of ecotheology terms with zero-shot prompts to large language models across a corpus of over 880,000 sentences from nine environmental NGOs. The rule-based approach consistently labels more sentences as religious than the LLMs, revealing a tension between vocabulary-based detection and contextual interpretation. The LLMs exhibit notable inconsistencies and prompt-sensitivity, especially in recognizing implicit or spiritual-language signals like 'Mother Earth' or 'sacred earth'. The findings highlight both the potential and the limits of LLMs for detecting religious language in digital corpora and underscore the ongoing debate about whether religiosity in language should be defined by terms or by context and meaning.

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.

Detecting Religious Language in Climate Discourse

TL;DR

This study addresses how religious language manifests within climate discourse by comparing a rule-based hierarchical tree of ecotheology terms with zero-shot prompts to large language models across a corpus of over 880,000 sentences from nine environmental NGOs. The rule-based approach consistently labels more sentences as religious than the LLMs, revealing a tension between vocabulary-based detection and contextual interpretation. The LLMs exhibit notable inconsistencies and prompt-sensitivity, especially in recognizing implicit or spiritual-language signals like 'Mother Earth' or 'sacred earth'. The findings highlight both the potential and the limits of LLMs for detecting religious language in digital corpora and underscore the ongoing debate about whether religiosity in language should be defined by terms or by context and meaning.

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.

Paper Structure

This paper contains 28 sections, 1 figure, 5 tables.

Figures (1)

  • Figure 1: Excerpt from the hierarchical tree with religious concepts.