While the research area of artificial intelligence benefited from increasingly sophisticated machine learning techniques in recent years, the resulting systems suffer from a loss of transparency and comprehensibility, especially for end-users. In this paper, we explore the effects of incorporating virtual agents into explainable artificial intelligence (XAI) designs on the perceived trust of end-users. For this purpose, we conducted a user study based on a simple speech recognition system for keyword classification. As a result of this experiment, we found that the integration of virtual agents leads to increased user trust in the XAI system. Furthermore, we found that the user's trust significantly depends on the modalities that are used within the user-agent interface design. The results of our study show a linear trend where the visual presence of an agent combined with a voice output resulted in greater trust than the output of text or the voice output alone. Additionally, we analysed the participants' feedback regarding the presented XAI visualisations. We found that increased human-likeness of and interaction with the virtual agent are the two most common mention points on how to improve the proposed XAI interaction design. Based on these results, we discuss current limitations and interesting topics for further research in the field of XAI. Moreover, we present design recommendations for virtual agents in XAI systems for future projects.

In many Western countries, non-formal education has become increasingly recognized as a valuable addition to the traditional educational system. In recent years, a special form of non-formal student laboratories (Schülerlabor) has emerged in Germany to promote primary and secondary practical science learning. This paper describes a developmental project on Schülerlabor learning environments for all students with a particular focus on sustainability education in the context of chemistry-related topics. The goal of reaching all students puts intentional pressure on the development process of learning environments. It forces the Schülerlabors to create a detailed model of differentiation, which can reach all learners of different interests and abilities. This also includes low-achievers and students who have disadvantaged educational biographies. In this sense, the structuring of non-formal learning environments simultaneously becomes a process of innovation with respect to both the curriculum and the teaching methods. In this paper, we present a corresponding model of differentiation and a specific example focusing on the learning about protecting and preserving metal objects in science education. Preliminary results and implications from the accompanying evaluation are also discussed.

Pain sensation is essential for survival, since it draws attention to physical threat to the body. Pain assessment is usually done through self-reports. However, self-assessment of pain is not available in the case of noncommunicative patients, and therefore, observer reports should be relied upon. Observer reports of pain could be prone to errors due to subjective biases of observers. Moreover, continuous monitoring by humans is impractical. Therefore, automatic pain detection technology could be deployed to assist human caregivers and complement their service, thereby improving the quality of pain management, especially for noncommunicative patients. Facial expressions are a reliable indicator of pain, and are used in all observer-based pain assessment tools. Following the advancements in automatic facial expression analysis, computer vision researchers have tried to use this technology for developing approaches for automatically detecting pain from facial expressions. This paper surveys the literature published in this field over the past decade, categorizes it, and identifies future research directions. The survey covers the pain datasets used in the reviewed literature, the learning tasks targeted by the approaches, the features extracted from images and image sequences to represent pain-related information, and finally, the machine learning methods used.

With advances in reinforcement learning (RL), agents are now being developed in high-stakes application domains such as healthcare and transportation. Explaining the behavior of these agents is challenging, as the environments in which they act have large state spaces, and their decision-making can be affected by delayed rewards, making it difficult to analyze their behavior. To address this problem, several approaches have been developed. Some approaches attempt to convey the global behavior of the agent, describing the actions it takes in different states. Other approaches devised local explanations which provide information regarding the agent's decision-making in a particular state. In this paper, we combine global and local explanation methods, and evaluate their joint and separate contributions, providing (to the best of our knowledge) the first user study of combined local and global explanations for RL agents. Specifically, we augment strategy summaries that extract important trajectories of states from simulations of the agent with saliency maps which show what information the agent attends to. Our results show that the choice of what states to include in the summary (global information) strongly affects people's understanding of agents: participants shown summaries that included important states significantly outperformed participants who were presented with agent behavior in a randomly set of chosen world-states. We find mixed results with respect to augmenting demonstrations with saliency maps (local information), as the addition of saliency maps did not significantly improve performance in most cases. However, we do find some evidence that saliency maps can help users better understand what information the agent relies on in its decision making, suggesting avenues for future work that can further improve explanations of RL agents.

Deep neural networks are successfully used for object and face recognition in images and videos. In order to be able to apply such networks in practice, for example in hospitals as a pain recognition tool, the current procedures are only suitable to a limited extent. The advantage of deep neural methods is that they can learn complex non-linear relationships between raw data and target classes without limiting themselves to a set of hand-crafted features provided by humans. However, the disadvantage is that due to the complexity of these networks, it is not possible to interpret the knowledge that is stored inside the network. It is a black-box learning procedure. Explainable Artificial Intelligence (AI) approaches mitigate this problem by extracting explanations for decisions and representing them in a human-interpretable form. The aim of this paper is to investigate the explainable AI methods Layer-wise Relevance Propagation (LRP) and Local Interpretable Model-agnostic Explanations (LIME). These approaches are applied to explain how a deep neural network distinguishes facial expressions of pain from facial expressions of emotions such as happiness and disgust.