Supporting students in developing diagnostic reasoning is a key challenge across educational domains. Novices often face cognitive biases such as premature closure and over-reliance on heuristics, and they struggle to transfer diagnostic strategies to new cases. Scenario-based learning (SBL) enhanced by Learning Analytics (LA) and large language models (LLM) offers a promising approach by combining realistic case experiences with personalized scaffolding. Yet, how different scaffolding approaches shape reasoning processes remains insufficiently explored. This study introduces PharmaSim Switch, an SBL environment for pharmacy technician training, extended with an LA- and LLM-powered pharmacist agent that implements pedagogical conversations rooted in two theory-driven scaffolding approaches: structuring and problematizing, as well as a student learning trajectory. In a between-groups experiment, 63 vocational students completed a learning scenario, a near-transfer scenario, and a far-transfer scenario under one of the two scaffolding conditions. Results indicate that both scaffolding approaches were effective in supporting the use of diagnostic strategies. Performance outcomes were primarily influenced by scenario complexity rather than students’ prior knowledge or the scaffolding approach used. The structuring approach was associated with more accurate Active and Interactive participation, whereas problematizing elicited more Constructive engagement. These findings underscore the value of combining scaffolding approaches when designing LA- and LLM-based systems to effectively foster diagnostic reasoning.

Language models can be used to provide interactive, personalized student feedback in educational settings.However, real-world deployment faces three key challenges: privacy concerns, limited computational resources, and the need for pedagogically valid responses.These constraints require small, open-source models that can run locally and reliably ground their outputs in correct information.We introduce SCRIBE, a framework for multi-hop, tool-augmented reasoning designed to generate valid responses to student questions about feedback reports.SCRIBE combines domainspecific tools with a self-reflective inference pipeline that supports iterative reasoning, tool use, and error recovery.We distil these capabilities into 3B and 8B models via two-stage LoRA fine-tuning on synthetic GPT-4o-generated data.Evaluation with a human-aligned GPT-Judge and a user study with 108 students shows that 8B-SCRIBE models achieve comparable or superior quality to much larger models in key dimensions such as relevance and actionability, while being perceived on par with GPT-4o and Llama-3.3 70B by students.These findings demonstrate the viability of SCRIBE for low-resource, privacy-sensitive educational applications.How can I improve my performance to pass the course? UsefulRelevant Actionable Correct Tools sort_student_features_with_importance Improve your performance by watching course videos more regularly and following a steady study routine -these habits strongly influence learning outcomes.I need to understand which specific behaviors were most affecting your performance in the course.This helped identify the most influential factors-mainly video load frequency and the number of study sessions.

Explainable Artificial Intelligence (XAI) seeks to render Artificial Intelligence (AI) models transparent and comprehensible, potentially increasing trust and confidence in AI recommendations. This research explores the realm of XAI within unsupervised educational machine learning, a relatively under-explored topic within Learning Analytics (LA). It introduces an XAI framework designed to elucidate clustering-based personalized recommendations for educators. Our approach involves a two-step validation: computational verification followed by domain-specific evaluation concerning its impact on teachers’ AI acceptance. Through interviews with K-12 educators, we identified key themes in teachers’ attitudes toward the explanations. The main contribution of this paper is a new XAI scheme for unsupervised educational machine-learning decision-support systems. The second is shedding light on the subjective nature of educators’ interpretation of XAI schemes and visualizations.

The increasing availability of Massive Open Online Courses (MOOCs) has created a necessity for personalized course recommendation systems. These systems often combine neural networks with Knowledge Graphs (KGs) to achieve richer representations of learners and courses. While these enriched representations allow more accurate and personalized recommendations, explainability remains a significant challenge which is especially problematic for certain domains with significant impact such as education and online learning. Recently, a novel class of recommender systems that uses reinforcement learning and graph reasoning over KGs has been proposed to generate explainable recommendations in the form of paths over a KG. Despite their accuracy and interpretability on e-commerce datasets, these approaches have scarcely been applied to the educational domain and their use in practice has not been studied. In this work, we propose an explainable recommendation system for MOOCs that uses graph reasoning. To validate the practical implications of our approach, we conducted a user study examining user perceptions of our new explainable recommendations. We demonstrate the generalizability of our approach by conducting experiments on two educational datasets: COCO and Xuetang.

Engaging students in argument from evidence is an essential goal of science education. This is a complex skill to develop; recent research in science education proposed the use of simulated classrooms to facilitate the practice of the skill. We use data from one such simulated environment to explore whether automated analysis of the transcripts of the teacher’s interaction with the simulated students using Natural Language Processing techniques could yield an accurate evaluation of the teacher’s performance. We are especially interested in explainable models that could also support formative feedback. The results are encouraging: Not only can the models score the transcript as well as humans can, but they can also provide justifications for the scores comparable to those provided by human raters.

AI-powered educational technology that is designed to support teachers in providing personalized instruction can enhance their ability to address the needs of individual students, hopefully leading to better learning gains. This paper presents results from a participatory research aimed at co-designing with science teachers a learning analytics tool that will assist them in implementing a personalized pedagogy in blended learning contexts. The development process included three stages. In the first, we interviewed a group of teachers to identify where and how personalized instruction may be integrated into their teaching practices. This yielded a clustering-based personalization strategy. Next, we designed a mock-up of a learning analytics tool that supports this strategy and worked with another group of teachers to define an ‘explainable learning analytics’ scheme that explains each cluster in a way that is both pedagogically meaningful and can be generated automatically. Third, we developed an AI algorithm that supports this ‘explainable clusters’ pedagogy and conducted a controlled experiment that evaluated its contribution to teachers’ ability to plan personalized learning sequences. The planned sequences were evaluated in a blinded fashion by an expert, and the results demonstrated that the experimental group – teachers who received the clusters with the explanations – designed sequences that addressed the difficulties exhibited by different groups of students better than those designed by teachers who received the clusters without explanations. The main contribution of this study is twofold. First, it presents an effective personalization approach that fits blended learning in the science classroom, which combines a real-time clustering algorithm with an explainable-AI scheme that can automatically build pedagogically meaningful explanations from item-level meta-data (Q Matrix). Second, it demonstrates how such an end-to-end learning analytics solution can be built with teachers through a co-design process and highlights the types of knowledge that teachers add to system-provided analytics in order to apply them to their local context. As a practical contribution, this process informed the design of a new learning analytics tool that was integrated into a free online learning platform that is being used by more than 1000 science teachers.

Evidence from various domains underlines the key role that human factors, and especially, trust, play in the adoption of technology by practitioners. In the case of Artificial Intelligence (AI) driven learning analytics tools, the issue is even more complex due to practitioners’ AI-specific misconceptions, myths, and fears (i.e., mass unemployment and ethical concerns). In recent years, artificial intelligence has been introduced increasingly into K-12 education. However, little research has been conducted on the trust and attitudes of K-12 teachers regarding the use and adoption of AI-based Educational Technology (EdTech).