[Paper] Mapping 99 emotion terms with GPT4 prompting reveals nuanced semantic conceptual structure
Mapping 99 emotion terms with GPT4 prompting reveals nuanced semantic conceptual structure Abstract Dimensional theories of emotion propose that affective experiences can be organised along continuous dimensions like Pleasure, Arousal, and Dominance. Recent computational methods for capturing these conceptual structures have relied primarily on word embeddings, requiring substantial technical expertise. This study examined whether prompting GPT4 as a more accessible method, can capture this structure more effectively, by comparing both approaches against human spatial reasoning, with particular focus on analysing extensive emotion vocabularies exceeding constraints of human cognitive capability. Study 1 established validity by testing six basic emotions, prompting showed strong convergence with human judgements, while embeddings produced fundamentally different clustering patterns. Study 2 extended analysis to 99 emotion terms. Both approaches identified two optimal clusters dist...