Visualizing emotions with linearly parameterized facial expressions

The key challenge of affective computing is to translate subjective emotional experiences intomeasurable data. Most recent advances in that field have relied on facial expressions asindicators for inner emotional states.Our current understanding of these expressions is categorical, i.e.there are some subjective feelings that are understood to be indicatedby specific faces. There is no agreed measure for their distance and noclear rule for how emotions can combine or do exclude.The computational processing of emotions therefore mostly relies oncompositional approaches using intependent dimensions, like valence and arousal. However, these methods lacka consistent mapping to a facial expression that turned out so crucial for theidentification of emotional states.This paper seeks to solve this problem by introducing a consistent facial visualizationfor a five dimensional model. A graphical representation as a comic style facial expression is provided inexamples, explanations and code. It visualizes emotions in a comically exaggerated style,similar to the successful emojis used in electronic communication.All graphical parameters depend linearly onthe input dimensions (valence, arousal, dominance, contempt and control).This might be a rough and crude method. It might not even be a good one,but it is at least something linear in the space of emotions.Empirical results from crowd workers confirm that the encoded emotionalinformation can be recorgnized intuitively and without further training.