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

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.

Accepted by Decision Support Systems (DSS)

References in corpus (6)

• Fake News Detection on Social Media: A Data Mining Perspective
• Predicting Process Behaviour using Deep Learning
• Decision support from financial disclosures with deep neural networks and transfer learning
• How Transferable are Neural Networks in NLP Applications?
• A Sentiment-and-Semantics-Based Approach for Emotion Detection in Textual Conversations
• Measuring Financial Sentiment to Predict Financial Instability: A New Approach based on Text Analysis

Cited by in corpus (10)

• Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertainty
• Sentiment analysis based on rhetorical structure theory: Learning deep neural networks from discourse trees
• HeBERT & HebEMO: a Hebrew BERT Model and a Tool for Polarity Analysis and Emotion Recognition
• Putting Question-Answering Systems into Practice: Transfer Learning for Efficient Domain Customization
• Multistage linguistic conditioning of convolutional layers for speech emotion recognition
• Quantum Federated Learning for Multimodal Data: A Modality-Agnostic Approach
• Deep Learning Neural Networks for Emotion Classification from Text: Enhanced Leaky Rectified Linear Unit Activation and Weighted Loss
• Text-based Emotion Aware Recommender
• REDAffectiveLM: Leveraging Affect Enriched Embedding and Transformer-based Neural Language Model for Readers' Emotion Detection
• An Affective Aware Pseudo Association Method to Connect Disjoint Users Across Multiple Datasets -- An Enhanced Validation Method for Text-based Emotion Aware Recommender