Decision support with text-based emotion recognition: Deep learning for affective computing

Emotions widely affect the decision-making of humans. This 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. Even though deep learning has evolved as the state-of-the-art in text mining, empirical investigations of its benefits for affective computing are scarce. We thus adapt recurrent neural networks from the field of deep learning to emotion recognition. In addition, we propose the use of transfer learning as an inductive knowledge transfer from related tasks in natural language processing. The resulting performance is evaluated in a holistic setting, where we find that both recurrent neural networks and transfer learning consistently outperforms traditional machine learning. Altogether, the findings have considerable implications for the use of affective computing in providing decision support.