Prompting Metaphoricity: Soft Labeling with Large Language Models in Popular Communication of Science Tweets in Spanish

AbstractIn this paper, we explore how large language models (LLMs) can be used to assign soft labels for metaphoricity in Popular Communication of Science (PCS) tweets written in Spanish. Instead of treating metaphors as a binary yes/no phenomenon, we focus on their graded nature and the variability commonly found in human annotations. Through a combination of prompt design and quantitative evaluation over a stratified sample of our dataset, we show that GPT-4 can assign probabilistic scores not only for general metaphoricity but also for specific metaphor types with consistency (Direct, Indirect, and Personification). The results show that, while LLMs align reasonably well with average human judgments for some categories, capturing the subtle patterns of inter-annotator disagreement remains a challenge. We present a corpus of 3,733 tweets annotated with LLM-generated soft labels, a valuable resource for further metaphor analysis in scientific discourse and figurative language annotation with LLMs.