Computational social systems (CSSs) focus on topics such as modelling, simulation, analysis, and understanding of social systems from the quantitative and/or computational perspective. "Systems" include man-man, man-machine, and machine-machine organizations and adversarial situations as well as social media structures and their dynamics. CSSs are becoming ever more complex with various kinds of data from diverse areas acquired by advanced data processing techniques, such as text, image, and video. Data-driven CSSs present characteristics of nonlinear dynamics, adaptability, robustness, and resilience. Dealing with complexity problems in CSSs is challenging because of the complex and unstructured characteristics of data, such as volume, variety, velocity, value, sequence, strong-relevance, accuracy, etc. Traditional methods have the problems of high computational complexity and low parallelism, which cannot meet the requirement of dealing with large-scale data. Thus, there is a great need for a powerful method that can deal with complexity problems in data-driven CSSs more efficiently and effectively in the age of big data.

Recently, cognition is emerging as a new and promising methodology with the development of cognitive-inspired computing, cognitive-inspired interaction, and systems. Cognitive computing, which is an important part of artificial intelligence, is able to solve a problem containing many entities linked together in a complex way with the model of perception, action, attention, learning and memory, decision making, language processing, communication, reasoning, problem solving, and consciousness aspects of cognition. The biggest advantage of cognitive computing is its ability to "understand" unstructured data, including language, images, and video. It has been proven to be effective in a wide spectrum of fields. For example, IBM Watson, the outstanding representative of cognitive computing systems, profoundly changed the way and efficiency of business problem-solving. Therefore, it is envisaged that cognitive computing-based solutions can overcome the emerging challenges in modern complexity problems by fully unleashing the potential of data-driven CSSs. Therefore, the investigation of cognitive computing-based solutions for complexity problems in CSSs is attracting more and more attention from both industry and academia.

The goal of this Special Issue is to provide a platform for high-quality contributions from academia, business, industry, and government that present recent advances in cognitive computing solutions for complexity problems in data-driven CSSs. Original research and review articles are welcome.

Potential topics include but are not limited to the following:

• Cognitive computing for complexity problems in CSSs
• Cognitive computing for complexity problems in socio-technical systems
• Cognitive computing for complexity problems in cyber-physical systems
• Big data-driven cognitive computing for CSSs
• Cognitive-inspired computing systems
• AI-assisted cognitive computing approaches
• Machine learning for decision support systems in CSSs
• Integration of cognitive computing and data science for CSSs
• Cognitive computing for analyzing nonlinear dynamics in CSSs
• Cognitive computing for improving robustness, and resilience in CSSs
• Cognitive computing solutions for trust, security, and privacy in CSSs
• Advanced learning methods for data-driven CSSs
• Application of new and novel cognitive computing methods in data-driven CSSs