This paper reports on a set of three recent experiments utilizing large-scale speech models to assess the oral reading fluency (ORF) of students in Ghana. While ORF is a well-established measure of foundational literacy, assessing it typically requires one-on-one sessions between a student and a trained rater, a process that is time-consuming and…

One-on-one tutoring is widely acknowledged as an effective instructional method, conditioned on qualified tutors. However, the high demand for qualified tutors remains a challenge, often necessitating the training of novice tutors (i.e., trainees) to ensure effective tutoring. Research suggests that providing timely explanatory feedback can…

Intelligent Tutoring Systems (ITS) possess significant potential to enhance learning outcomes. However, deploying ITSs in global south countries presents challenges due to their frequent lack of essential technological resources, such as computers and internet access. The concept of AIED Unplugged has emerged to bridge this digital divide,…

An important component of many Adaptive Instructional Systems (AIS) is a 'Learner Model' intended to track student learning and predict future performance. Predictions from learner models are frequently used in combination with mastery criterion decision rules to make pedagogical decisions. Important aspects of learner models, such as learning…

Collaborative learning offers numerous benefits to learners, largely due to the dialogue that is unfolding between them. However, there is still much to learn about the structure of collaborative dialogue, and especially little is known about co-creative dialogues during learning. This paper reports on a study with learners engaged in co-creative…

Autograding short textual answers has become much more feasible due to the rise of NLP and the increased availability of question-answer pairs brought about by a shift to online education. Autograding performance is still inferior to human grading. The statistical and black-box nature of state-of-the-art machine learning models makes them…

The emergence of Large Language Models (LLMs) has marked a significant change in education. The appearance of these LLMs and their associated chatbots has yielded several advantages for both students and educators, including their use as teaching assistants for content creation or summarisation. This paper aims to evaluate the capacity of LLMs…

Large language models (LLMs) offer an opportunity to make large-scale changes to educational content that would otherwise be too costly to implement. The work here highlights how LLMs (in particular GPT-4) can be prompted to revise educational math content ready for large scale deployment in real-world learning environments. We tested the ability…

Hypothesis testing involves a complex stepwise procedure that is challenging for many students in introductory university statistics courses. In this paper we assess how feedback from an Intelligent Tutoring System can address the logic of hypothesis testing and whether such feedback contributes to first-year social sciences students' proficiency…

Automatic essay scoring (AES) refers to the process of scoring free text responses to given prompts, considering human grader scores as the gold standard. Writing such essays is an essential component of many language and aptitude exams. Hence, AES became an active and established area of research, and there are many proprietary systems used in…

The ideas behind the constraint-based modeling (CBM) approach to the design of intelligent tutoring systems (ITSs) grew out of attempts in the 1980's to clarify how declarative and procedural knowledge interact during skill acquisition. The learning theory that underpins CBM was based on two conceptual innovations. The first innovation was to…

The order of problems presented to students is an important variable that affects learning effectiveness. Previous studies have shown that solving problems in a blocked order, in which all problems of one type are completed before the student is switched to the next problem type, results in less effective performance than does solving the problems…

Student modeling is a fundamental concept applicable to a variety of intelligent tutoring systems (ITS). However, there is not a lot of practical guidance on how to construct and train such models. This paper compares two approaches for student modeling, Knowledge Tracing (KT) and Performance Factors Analysis (PFA), by evaluating their predictive…

In this paper, we introduce logic programming as a domain that exhibits some characteristics of being ill-defined. In order to diagnose student errors in such a domain, we need a means to hypothesise the student's intention, that is the strategy underlying her solution. This is achieved by weighting constraints, so that hypotheses about solution…

Policy problems like "What should we do about global warming?" are ill-defined in large part because we do not agree on a system to represent them the way we agree Algebra problems should be represented by equations. As a first step toward building a policy deliberation tutor, we investigated: (a) whether causal diagrams help students learn to…