Adaptive learning platforms can personalise learning in classrooms, yet teachers need tools to monitor student progress and rapidly identify students who need additional attention. Monitoring dashboards that detect outlier students can fulfil this need, but insufficient explanation of the detection logic may undermine trust and lead to inappropriate use. To address this challenge, we iteratively designed and implemented a real-time monitoring dashboard with model-centric and data-centric explanations, informed by teacher input. We then conducted a counterbalanced within-group experiment with follow-up interviews to study how 11 teachers used the dashboard in a real classroom and how they engaged with the explanations to calibrate their trust. We found that teachers successfully integrated the dashboard into their classes, and that their trust was shaped by many dispositional, situational, and learnt factors. Crucially, the data-centric explanations enabled teachers to validate the accuracy of outlier predictions, check alignment with their prior knowledge of students, and identify suitable interventions. Based on these findings, we present design recommendations for explainable outlier detection systems in education.

Personalized problem selection enhances student practice in tutoring systems.Prior research has focused on transparent problem selection that supports learner control but rarely engages learners in selecting practice materials.We explored how different levels of control (i.e., full AI control, shared control, and full learner control), combined with showing learning analytics on skill mastery and visual what-if explanations, can support students in practice contexts requiring high degrees of self-regulation, such as homework.Semistructured interviews with six middle school students revealed three key insights: (1) participants highly valued learner control for an enhanced learning experience and better self-regulation, especially because most wanted to avoid losses in skill mastery;(2) only seeing their skill mastery estimates often made participants base problem selection on their weaknesses; and (3) what-if explanations stimulated participants to focus more on their strengths and improve skills until they were mastered.These findings show how explainable learning analytics could shape students' selection strategies when they have control over what to practice.They suggest promising avenues for helping students learn to regulate their effort, motivation, and goals during practice with tutoring systems.

E-learning platforms that personalise content selection with AI are often criticised for lacking transparency and controllability. Researchers have therefore proposed solutions such as open learner models and letting learners select from ranked recommendations, which engage learners before or after the AI-supported selection process. However, little research has explored how learners - especially adolescents - could engage during such AI-supported decision-making. To address this open challenge, we iteratively designed and implemented a control mechanism that enables learners to steer the difficulty of AI-compiled exercise series before practice, while interactively analysing their control's impact in a 'what-if' visualisation. We evaluated our prototypes through four qualitative studies involving adolescents, teachers, EdTech professionals, and pedagogical experts, focusing on different types of visual explanations for recommendations. Our findings suggest that 'why' explanations do not always meet the explainability needs of young learners but can benefit teachers. Additionally, 'what-if' explanations were well-received for their potential to boost motivation. Overall, our work illustrates how combining learner control and visual explanations can be operationalised on e-learning platforms for adolescents. Future research can build upon our designs for 'why' and 'what-if' explanations and verify our preliminary findings.

Recent advancements in Educational AI have focused on models for automatic question generation. Yet, these advancements face challenges: (1) their "black-box" nature limits transparency, thereby obscuring the decision-making process; and (2) their novelty sometimes causes inaccuracies due to limited feedback systems. Explainable AI (XAI) aims to address the first limitation by clarifying model decisions, while Interactive Machine Learning (IML) emphasises user feedback and model refinement. However, both XAI and IML solutions primarily serve AI experts, often neglecting novices like teachers. Such oversights lead to issues like misaligned expectations and reduced trust. Following the user-centred design method, we collaborated with teachers and ed-tech experts to develop an AI-aided system for generating multiple-choice question distractors, which incorporates feedback, control, and visual explanations. Evaluating these through semi-structured interviews with 12 teachers, we found a strong preference for the feedback feature, enabling teacher-guided AI improvements. Control and explanations’ usefulness was largely dependent on model performance: they were valued when the model performed well. If the model did not perform well, teachers sought context over AI-centric explanations, suggesting a tilt towards data-centric explanations. Based on these results, we propose guidelines for creating tools that enable teachers to steer and interact with question-generating AI models.

Explainable artificial intelligence is increasingly used in machine learning (ML) based decision-making systems in healthcare. However, little research has compared the utility of different explanation methods in guiding healthcare experts for patient care. Moreover, it is unclear how useful, understandable, actionable and trustworthy these methods are for healthcare experts, as they often require technical ML knowledge. This paper presents an explanation dashboard that predicts the risk of diabetes onset and explains those predictions with data-centric, feature-importance, and example-based explanations. We designed an interactive dashboard to assist healthcare experts, such as nurses and physicians, in monitoring the risk of diabetes onset and recommending measures to minimize risk. We conducted a qualitative study with 11 healthcare experts and a mixed-methods study with 45 healthcare experts and 51 diabetic patients to compare the different explanation methods in our dashboard in terms of understandability, usefulness, actionability, and trust. Results indicate that our participants preferred our representation of data-centric explanations that provide local explanations with a global overview over other methods. Therefore, this paper highlights the importance of visually directive data-centric explanation method for assisting healthcare experts to gain actionable insights from patient health records. Furthermore, we share our design implications for tailoring the visual representation of different explanation methods for healthcare experts.

Researchers have widely acknowledged the potential of control mechanisms with which end-users of recommender systems can better tailor recommendations. However, few e-learning environments so far incorporate such mechanisms, for example for steering recommended exercises. In addition, studies with adolescents in this context are rare. To address these limitations, we designed a control mechanism and a visualisation of the control’s impact through an iterative design process with adolescents and teachers. Then, we investigated how these functionalities affect adolescents’ trust in an e-learning platform that recommends maths exercises. A randomised controlled experiment with 76 middle school and high school adolescents showed that visualising the impact of exercised control significantly increases trust. Furthermore, having control over their mastery level seemed to inspire adolescents to reasonably challenge themselves and reflect upon the underlying recommendation algorithm. Finally, a significant increase in perceived transparency suggested that visualising steering actions can indirectly explain why recommendations are suitable, which opens interesting research tracks for the broader field of explainable AI.

In the scope of explainable artificial intelligence, explanation techniques are heavily studied to increase trust in recommender systems. However, studies on explaining recommendations typically target adults in e-commerce or media contexts; e-learning has received less research attention. To address these limits, we investigated how explanations affect adolescents’ initial trust in an e-learning platform that recommends mathematics exercises with collaborative filtering. In a randomized controlled experiment with 37 adolescents, we compared real explanations with placebo and no explanations. Our results show that real explanations significantly increased initial trust when trust was measured as a multidimensional construct of competence, benevolence, integrity, intention to return, and perceived transparency. Yet, this result did not hold when trust was measured one-dimensionally. Furthermore, not all adolescents attached equal importance to explanations and trust scores were high overall. These findings underline the need to tailor explanations and suggest that dynamically learned factors may be more important than explanations for building initial trust. To conclude, we thus reflect upon the need for explanations and recommendations in e-learning in low-stakes and high-stakes situations.