Emotion Classification: How Does an Automated System Compare to Naive Human Coders?

TL;DR

This study compares automated emotion classification systems with naive human coders, showing that the computer outperforms humans in classifying speech emotions and can improve accuracy by abstaining from uncertain classifications.

Contribution

It provides a comprehensive comparison between state-of-the-art automated systems and naive human coders in speech emotion classification tasks.

Findings

The computer system outperforms naive human coders in most emotion classification cases.

The system's accuracy improves when it rejects uncertain utterances.

Humans do not significantly improve accuracy when only considering confident classifications.

Abstract

The fact that emotions play a vital role in social interactions, along with the demand for novel human-computer interaction applications, have led to the development of a number of automatic emotion classification systems. However, it is still debatable whether the performance of such systems can compare with human coders. To address this issue, in this study, we present a comprehensive comparison in a speech-based emotion classification task between 138 Amazon Mechanical Turk workers (Turkers) and a state-of-the-art automatic computer system. The comparison includes classifying speech utterances into six emotions (happy, neutral, sad, anger, disgust and fear), into three arousal classes (active, passive, and neutral), and into three valence classes (positive, negative, and neutral). The results show that the computer system outperforms the naive Turkers in almost all cases. Furthermore, the computer system can increase the classification accuracy by rejecting to classify utterances for which it is not confident, while the Turkers do not show a significantly higher classification accuracy on their confident utterances versus unconfident ones.