In Emotion Detection within Natural Language Processing and related multimodal research, the growth of datasets and models has led to a challenge: disparities in emotion classification methods. The lack of commonly agreed upon conventions on the classification of emotions creates boundaries for model comparisons and dataset adaptation. In this paper, we compare the current classification methods in recent models and datasets and propose a valid method to combine different emotion categories. Our proposal arises from experiments across models, psychological theories, and human evaluations, and we examined the effect of proposed mapping on models.

Positive emotion elicitation aims at evoking positive emotion states in human users in open-domain dialogue generation. However, most work focuses on inducing a single-dimension of positive sentiment using human annotated datasets, which limits the scale of the training dataset. In this paper, we propose to model various emotions in large unannotated conversations, such as joy, trust and anticipation, by leveraging a latent variable to control the emotional intention of the response. Our proposed emotion-eliciting-Conditional-Variational-AutoEncoder (EE-CVAE) model generates more diverse and emotionally-intelligent responses compared to single-dimension baseline models in human evaluation.