Defining Character Computing from the Perspective of Computer Science and Psychology

The emerging field of Character Computing aims at combining computer science and Psychology to achieve human-aware computing that considers all aspects of human behavior and human experience, including the human user's states, traits, and surrounding situations. We propose developing an computational and psychologically-driven architecture for Character Computing based on existing accepted psychological models of cognition, personality and emotions. This would help towards further defining Character Computing and setting strong theoretical foundations for it. The computational architecture is at the heart of this PHD thesis. Developing the architecture requires input from Psychology and Computer Science which is currently already ensured by continuous input from the supervisors Prof. Cornelia Herbert (Ulm University) and Prof. Slim Abdennadher (GUC). Beta-versions of the architecture are then tested in experimental psychological experiments and use-cases that would most benefit from considering the character of the user as a component. The situations most telling and affected by that are investigated through machine learning techniques, experimental psychological methods and computational modeling. The use-cases range from IoT applications, smart assistants, autonomous cars to health care and education.