Communication aiming to persuade an audience uses strategies to frame certain entities in ‘character roles’ such as hero, villain, victim, or beneficiary, and to build narratives around these ascriptions. The Character-Role Framework is an approach to model these narrative strategies, which has been used extensively in the Social Sciences and is just beginning to get attention in Natural Language Processing (NLP). This work extends the framework to scientific editorials and social media texts within the domains of ecology and climate change. We identify characters’ roles across expanded categories (human, natural, instrumental) at the entity level, and present two annotated datasets: 1,559 tweets from the Ecoverse dataset and 2,150 editorial paragraphs from Nature & Science. Using manually annotated test sets, we evaluate four state-of-the-art Large Language Models (LLMs) (GPT-4o, GPT-4, GPT-4-turbo, LLaMA-3.1-8B) for character-role detection and categorization, with GPT-4 achieving the highest agreement with human annotators. We then apply the best-performing model to automatically annotate the full datasets, introducing a novel entity-level resource for character-role analysis in the environmental domain.

The widespread use of Large Language Models (LLMs), particularly among non-expert users, has raised ethical concerns about the propagation of harmful biases. While much research has addressed social biases, few works, if any, have examined anthropocentric bias in Natural Language Processing (NLP) technology. Anthropocentric language prioritizes human value, framing non-human animals, living entities, and natural elements solely by their utility to humans; a perspective that contributes to the ecological crisis. In this paper, we evaluate anthropocentric bias in OpenAI’s GPT-4o across various target entities, including sentient beings, non-sentient entities, and natural elements. Using prompts eliciting neutral, anthropocentric, and ecocentric perspectives, we analyze the model’s outputs and introduce a manually curated glossary of 424 anthropocentric terms as a resource for future ecocritical research. Our findings reveal a strong anthropocentric bias in the model’s responses, underscoring the need to address human-centered language use in AI-generated text to promote ecological well-being.

Anthropogenic ecological crisis constitutes a significant challenge that all within the academy must urgently face, including the Natural Language Processing (NLP) community. While recent years have seen increasing work revolving around climate-centric discourse, crucial environmental and ecological topics outside of climate change remain largely unaddressed, despite their prominent importance. Mainstream NLP tasks, such as sentiment analysis, dominate the scene, but there remains an untouched space in the literature involving the analysis of environmental impacts of certain events and practices. To address this gap, this paper presents EcoVerse, an annotated English Twitter dataset of 3,023 tweets spanning a wide spectrum of environmental topics. We propose a three-level annotation scheme designed for Eco-Relevance Classification, Stance Detection, and introducing an original approach for Environmental Impact Analysis. We detail the data collection, filtering, and labeling process that led to the creation of the dataset. Remarkable Inter-Annotator Agreement indicates that the annotation scheme produces consistent annotations of high quality. Subsequent classification experiments using BERT-based models, including ClimateBERT, are presented. These yield encouraging results, while also indicating room for a model specifically tailored for environmental texts. The dataset is made freely available to stimulate further research.