Deep learning for affective computing: text-based emotion recognition in decision support

TL;DR

This paper advances emotion recognition in text for decision support by customizing deep recurrent neural networks and introducing sent2affect, a transfer learning approach, demonstrating superior performance over traditional methods across multiple datasets.

Contribution

It proposes a novel transfer learning method called sent2affect for emotion recognition and customizes RNN architectures for improved accuracy in affective computing tasks.

Findings

Recurrent neural networks outperform traditional machine learning methods.

Transfer learning with sent2affect improves emotion recognition accuracy.

The approach performs well across six benchmark datasets.

Abstract

Emotions widely affect human decision-making. This fact is taken into account by affective computing with the goal of tailoring decision support to the emotional states of individuals. However, the accurate recognition of emotions within narrative documents presents a challenging undertaking due to the complexity and ambiguity of language. Performance improvements can be achieved through deep learning; yet, as demonstrated in this paper, the specific nature of this task requires the customization of recurrent neural networks with regard to bidirectional processing, dropout layers as a means of regularization, and weighted loss functions. In addition, we propose sent2affect, a tailored form of transfer learning for affective computing: here the network is pre-trained for a different task (i.e. sentiment analysis), while the output layer is subsequently tuned to the task of emotion recognition. The resulting performance is evaluated in a holistic setting across 6 benchmark datasets, where we find that both recurrent neural networks and transfer learning consistently outperform traditional machine learning. Altogether, the findings have considerable implications for the use of affective computing.