The traditional Elo rating system (ERS), widely used as a student model in adaptive learning systems, assumes unidimensionality (i.e., all items measure a single ability or skill), limiting its ability to handle multidimensional data common in educational contexts. In response, several multidimensional extensions of the Elo rating system have been…

Algorithmic bias is a pressing concern in educational data mining (EDM), as it risks amplifying inequities in learning outcomes. The Area Between ROC Curves (ABROCA) metric is frequently used to measure discrepancies in model performance across demographic groups to quantify overall model fairness. However, its skewed distribution--especially when…

When tutoring students it is useful to be able to predict whether they are succeeding as early as possible. This paper compares multiple methods for predicting from sequential interaction data whether a student is on a successful path. Predicting students' future performance and intervening has shown promise in improving learner outcomes and…

Online educational technologies facilitate pedagogical experimentation, but typical experimental designs assign a fixed proportion of students to each condition, even if early results suggest some are ineffective. Experimental designs using multi-armed bandit (MAB) algorithms vary the probability of condition assignment for a new student based on…

Discrimination and social determinants of health significantly affect patient care among transgender and gender diverse (TGD) people. The challenges that TGD people face within the healthcare setting are partially attributed to a lack of gender-affirming care education and training for health professionals. Although research is limited on…

Fully-Latent Principal Stratification (FLPS) offers a promising approach for estimating treatment effect heterogeneity based on patterns of students' interactions with Intelligent Tutoring Systems (ITSs). However, FLPS relies on correctly specified models. In addition, multiple latent variables, such as ability, participation, and epistemic…

This study investigates the capabilities of Large Language Models to simulate counselling clients in educational role-plays in comparison to human role-players. Initially, we recorded role-playing sessions, where novice counsellors interacted with human peers acting as clients, followed by role-plays between humans and clients simulated by…

The construct of static and emergent shape thinking (Moore & Thompson, 2015) characterizes differences in students' reasoning about graphs. In our previous work with middle school students, we found that this construct may also be useful in characterizing students' reasoning about other representations such as simulations and tables. In this…

Working collaboratively in groups can positively impact performance and student engagement. Intelligent social agents can provide a source of personalized support for students, and their benefits likely extend to collaborative settings, but it is difficult to determine how these agents should interact with students. Reinforcement learning (RL)…

Reading comprehension is essential for both knowledge acquisition and memory reinforcement. Automated modeling of the comprehension process provides insights into the efficacy of specific texts as learning tools. This paper introduces an improved version of the Automated Model of Comprehension, version 3.0 (AMoC v3.0). AMoC v3.0 is based on two…

Promptly and properly addressing students' help requests during office hours is a critical challenge for large CS courses. With a large amount of help requests, instructors often find themselves facing a long office hours queue and need to decide who to help next. Most instructors typically select the earliest arrival students (FCFS), while some…

Personalized learning stems from the idea that students benefit from instructional material tailored to their needs. Many online learning platforms purport to implement some form of personalized learning, often through on-demand tutoring or self-paced instruction, but to our knowledge none have a way to automatically explore for specific…

Peer-mediation in a school environment, when carried out correctly, can benefit not only the parties of the conflict, but also their environment, including the school, the team, the family and the mediator. A serious same has been designed and a prototype developed for the training of minors and young adults as mediators. The core of the game is a…

In this paper, the SOLO taxonomy is used to identify different levels of student understanding of the statistical concepts associated with sampling distribution. This study was part of a research project investigating students' conceptual understanding of concepts of hypothesis testing taught with the support of simulation learning activities. The…

Adaptive learning is an area of educational technology that consists in delivering personalized learning experiences to address the unique needs of each learner. An important subfield of adaptive learning is learning path personalization: it aims at designing systems that recommend sequences of educational activities to maximize students' learning…