Lifestyle-related diseases like type 2 diabetes mellitus (T2DM) and chronic obstructive pulmonary disease (COPD), have a major impact on society, asking for comprehensive disease management support. While AI technology has advanced for diagnosis and disease detection, its implementation into eHealth and mHealth applications remains limited, with low adoption rates and limited evidence of effectiveness. To achieve the necessary levels of client engagement and self-efficacy in chronic disease lifestyle management (CDLM), Artificial Intelligence (AI) support must demonstrate social competencies throughout its entire lifecycle—an under-researched topic. This paper introduces a novel Social AI Competence framework designed to provide durable personalized CDLM-support. The framework defines four complementary core competencies: (1) supporting meaningful activities, (2) providing responsible actionable explanations, (3) engaging persons in reflective interactions, and (4) strengthening and leveraging support networks. Underlying these competencies are eleven key social skills, detailed in terms of their foundation, functionality, state-of-the-art advancements, and research and development challenges. The CDLM system under development employs interactive modeling techniques to incorporate the experience and expertise of both experts and clients into these skills, supported by a modular architecture that ensures adaptability and scalability. Integrating social AI functions into the competency framework enables systematic assessment and optimization of their proportional effectiveness in real-world use cases.

We present SHARPIE (Shared Human-AI Reinforcement Learning Platform for Interactive Experiments), a generic framework to support experiments with RL agents and humans. It consists of a versatile wrapper for RL environments and algorithm libraries, a participant-facing web interface, logging utilities, and deployment on popular cloud and participant recruitment platforms. It empowers researchers to study a wide variety of research questions related to the interaction between humans and RL agents and aims to standardize the field of study on RL in human contexts.

Numerous research efforts have centered on identifying the most influential players in networked social systems. This problem is immensely crucial in the research of complex networks. Most existing techniques either model social dynamics on static networks only and ignore the underlying time-serial nature or model the social interactions as temporal edges without considering the influential relationship between them. In this paper, we propose a novel perspective of modeling social interaction data as the graph on event sequence, as well as the Soft K-Shell algorithm that analyzes not only the network’s local and global structural aspects, but also the underlying spreading dynamics. The extensive experiments validated the efficiency and feasibility of our method in various social networks from real world data. To the best of our knowledge, this work is the first of its kind.

Behavior change support systems need to take into account individual needs and preferences to provide appropriate support. In this demonstration, we illustrate how this might be achieved through the explicit modeling of user characteristics within knowledge graphs (KG), captured in a dialogue between the system and the user. We demonstrate how up-to-date information enables reasoning for providing personalized support.