Search for: All records

Training emotion recognition models has relied heavily on human annotated data, which present diversity, quality, and cost challenges. In this paper, we explore the potential of Large Language Models (LLMs), specifically GPT-4, in automating or assisting emotion annotation. We compare GPT-4 with supervised models and/or humans in three aspects: agreement with human annotations, alignment with human perception, and impact on model training. We find that common metrics that use aggregated human annotations as ground truth can underestimate GPT-4's performance, and our human evaluation experiment reveals a consistent preference for GPT-4 annotations over humans across multiple datasets and evaluators. Further, we investigate the impact of using GPT-4 as an annotation filtering process to improve model training. Together, our findings highlight the great potential of LLMs in emotion annotation tasks and underscore the need for refined evaluation methodologies. 

Emotions provide critical information regarding a person's health and well-being. Therefore, the ability to track emotion and patterns in emotion over time could provide new opportunities in measuring health longitudinally. This is of particular importance for individuals with bipolar disorder (BD), where emotion dysregulation is a hallmark symptom of increasing mood severity. However, measuring emotions typically requires self-assessment, a willful action outside of one's daily routine. In this paper, we describe a novel approach for collecting real-world natural speech data from daily life and measuring emotions from these data. The approach combines a novel data collection pipeline and validated robust emotion recognition models. We describe a deployment of this pipeline that included parallel clinical and self-report measures of mood and self-reported measures of emotion. Finally, we present approaches to estimate clinical and self-reported mood measures using a combination of passive and self-reported emotion measures. The results demonstrate that both passive and self-reported measures of emotion contribute to our ability to accurately estimate mood symptom severity for individuals with BD.