In using large language models (LLMs) for education, such as distractors in multiple-choice questions and learning by teaching, error-containing content is used. Prompt tuning and retraining LLMs are possible ways of having LLMs generate error-containing sentences in the learning content. However, there needs to be more discussion on how to tune…

Knowledge components (KCs) have many applications. In computing education, knowing the demonstration of specific KCs has been challenging. This paper introduces an entirely data-driven approach for: (1) discovering KCs; and (2) demonstrating KCs, using students' actual code submissions. Our system is based on two expected properties of KCs: (1)…

Neural networks are ubiquitous in applied machine learning for education. Their pervasive success in predictive performance comes alongside a severe weakness, the lack of explainability of their decisions, especially relevant in humancentric fields. We implement five state-of-the-art methodologies for explaining black-box machine learning models…

Knowledge Tracing (KT) is a task to model students' knowledge based on their coursework interactions within an Intelligent Tutoring System (ITS). Recently, Deep Neural Networks (DNN) showed superb performance over classical methods on multiple dataset benchmarks. While most Deep Learning based Knowledge Tracing (DLKT) models are optimized for…

This study aimed to compare the effectiveness and efficiency of the model-lead-test (MLT) and video modeling (VM) methods in teaching individuals with ID how to access and use the services provided by the Turkish state in digital environments. Four individuals participated in the study, in which the adapted alternating treatments design, one of…

The roles in traditional mentoring dyads are well known across both academic and professional contexts (Dawson, 2014). Despite the universality of these relationships, the way mentorship is evaluated in these relationships is fractured. Evaluation is limited to singular voices, singular points in time and simplified metrics to capture the journey…

How can we test whether state-of-the-art generative models, such as Blender and GPT-3, are good AI teachers, capable of replying to a student in an educational dialogue? Designing an AI teacher test is challenging: although evaluation methods are much-needed, there is no off-the-shelf solution to measuring pedagogical ability. This paper reports…

Although statistical practices to evaluate intervention effects in SCEDs have gained prominence in the recent times, models are yet to incorporate and investigate all their analytic complexities. Most of these statistical models incorporate slopes and autocorrelations both of which contribute to trend in the data. The question that arises is…

The COVID-19 pandemic has tackled global sustainability without prejudice or geographical constraint. It has also prompted people to advance to the post-pandemic era. However, it is possible that in the future, extreme negative effects in response to crisis, especially during a pandemic, would recur. In fact, it might worsen. This situation has…

The current research paper investigates the impact of McCarthy's 4MAT model on developing writing skills among upper-grade primary pupils. Sixty-four pupils in six primary-stage grades were chosen as the study participants and were divided randomly into two matched groups (a control group and an experimental one). The researcher adopted the…

As students learn how to program, both their programming code and their understanding of it evolves over time. In this work, we present a general data-driven approach, named "Temporal-ASTNN" for modeling student learning progression in open-ended programming domains. Temporal-ASTNN combines a novel neural network model based on abstract…

The explosion of Open Educational Resources (OERs) in the recent years creates the demand for scalable, automatic approaches to process and evaluate OERs, with the end goal of identifying and recommending the most suitable educational materials for learners. We focus on building models to find the characteristics and features involved in…

As problems become increasingly complex, science educators need to better understand how new knowledge is constructed and applied in heterogeneous team collaborations, and how to teach students to productively engage in these processes. We discuss the emergence of insights in collaborative sensemaking and suggest a model that articulates the…

Automatic short answer grading is an important research direction in the exploration of how to use artificial intelligence (AI)-based tools to improve education. Current state-of-the-art approaches use neural language models to create vectorized representations of students responses, followed by classifiers to predict the score. However, these…

This work explores how population-based engagement prediction can address cold-start at scale in large learning resource collections. The paper introduces: (1) VLE, a novel dataset that consists of content and video based features extracted from publicly available scientific video lectures coupled with implicit and explicit signals related to…