Are More Emotion Theories Better? Joint Prompting Improves Emotion Categorization Robustness
Abstract
AbstractEmotion analysis systems are expected by users to provide reliable results. Optimizing their robustness, in addition to accuracy, is particularly challenging in noisy environments, such as social media data or other forms of naturally expressed language. Our hypothesis is that robustness can be improved by guiding a language model to pay attention to multiple emotion signals in the input text. Therefore, requesting labels according to multiple emotion theories may improve robustness. To study this hypothesis, we run permutation experiments on input instances to test the robustness of LLM configurations based on basic emotions only, and jointly with valence–arousal, and cognitive appraisals. We find that adding valence–arousal and cognitive appraisal along with basic emotion instructions to the emotion classification improves robustness, with the effect being most pronounced for adding appraisals. In a further analysis, we find that this improvement is less susceptible to word order permutations and more to random word substitutions and deletions. These differences hold across multiple LLMs studied in our work.