Emotion, which originally belongs to the unique and complex internal attribute of human individuals, is becoming a form of productivity reconstructed by technology simulations and business. Now it comes to us in the way of human-computer interaction. Currently, with the development of information technology, the Internet of things (IoT), based on the Internet and sensor devices, combined with mobile edge computing and 5G technology, constitutes a ubiquitous network. The rise of wearable devices also enables all network devices to act as the carrier of emotional interaction. With the help of these new technologies, emotional artificial intelligence (AI) has broad application prospects in the fields of intelligent transportation, medical care, media entertainment, enterprise management, and so on. For example, in the field of enterprise management, the emotional artificial intelligence adopted by enterprises can produce empathy and understanding for each customer when they need it. It enables enterprises to recommend the right products and services to the right customers at the right time, so as to improve customer participation. At the present time, the work of experts in the field of emotional artificial intelligence mainly focuses on basic emotion analysis and artificial emotion simulation. Emotion recognition is mainly achieved through the study of various modal data such as human facial expression, voice intonation, text content, and body physiological signals, so as to recognize various human emotions and emotional states. Taking facial expression recognition as an example, expression recognition technology can use the facial information of the human face, such as the changes of fine lines at the corners of eyes, eyebrows and corners of the mouth, to judge the expression.

Emotion recognition is only the most basic step of emotion computing. When AI begins to try to give feedback with emotional expression and emotional decision-making, man-machine emotional interaction can establish a complete closed loop. Emotion itself is highly complex and abstract. Neuroscience knows little about the neural mechanism or neural circuit of emotion, and there is also a lack of effective technical methods to objectively and quantitatively study the emotion model from the system level. In addition, from the perspective of the development process of artificial intelligence, the research of emotional intelligence has only recently attracted the attention of academia and industry, while the research of emotional artificial intelligence started late.

This Special Issue aims to study the latest developments, new architecture, and new algorithms of emotional artificial intelligence driven by mobile edge computing and 5G technology. This Special Issue will provide opportunities for researchers in the field of computational intelligence and computational neuroscience, including facial expression recognition, human-computer speech emotion interaction, text-based emotion recognition, multi-modal emotion recognition, and so on. We welcome original research and review articles.

Potential topics include but are not limited to the following:

• Architecture design of wearable Internet of things
• Facial micro-expression recognition based on deep learning
• Machine synthesis algorithm of humanoid speech based on transfer learning and reinforcement learning
• Robot cognition-emotion interaction model
• Emotional interaction between users and artificial intelligence
• Emotional semantic analysis based on natural language processing
• Emotion recognition and intention prediction based on text
• Machine learning model of emotional artificial intelligence
• Privacy protection algorithm in emotional AI Internet of things
• Multi-modal emotion data collection and processing based on intelligent terminal equipment
• Multi-modal emotion feature classification based on support vector machines
• Personalized emotion model in the Internet of things