In online mathematics education, self-explanation is increasingly recognized as a key tool for improving learning outcomes. Identifying learning impasses, which present significant educational challenges, is crucial. Typically, detecting these impasses demands considerable effort from educators to manually review and identify issues in students’ mathematical reasoning.This paper introduces a fully automated impasse detection system designed for online math learning that leverages self-explanations. The system collects high-quality data from students working on the same quizzes, generates example answers, and uses these as benchmarks to identify where students are struggling. The system architecture is described in detail, focusing on the methods used to gather and validate high-quality self-explanation data.Empirical analysis using text regression models shows promising results: the models predict self-explanation scores with an error rate of 0.585 for validation data and 0.655 for evaluation data. While there are variations in scoring accuracy across different mathematical topics, the findings suggest that the system has the potential to significantly improve mathematics education by automating the detection of learning impasses.

In the field of mathematics education, self-explanation is recognized as a critical facilitator for learners to articulate their understanding of complex mathematical concepts and problem-solving techniques. With the emergence of digital learning platforms, the potential to utilize such self-explanations for automated evaluation has expanded, yet significant challenges remain. This study introduces a method that integrates vision and language models to enhance the accuracy of automated evaluations of self-explanations in mathematics quizzes. By leveraging the CLIP encoder, we utilize features from both handwritten images and textual self-explanations, aiming to incorporate the characteristics of handwritten solutions that have been overlooked by text-only evaluations. Models were developed to include self-explanations alone (baseline) and those that integrate image features, using both the original and a fine-tuned CLIP encoder adapted to our dataset of self-explanations and handwritten images. Experimental results demonstrated that the model utilizing the fine-tuned CLIP significantly outperformed the baseline, showing a notable reduction in MAE. Conversely, the model employing the original CLIP encoder exhibited decreased performance compared to the baseline, revealing the complex interplay between integrating self-explanations and image features. These findings suggest that the benefits of embedding image features depend on the quality and appropriateness of the visual data incorporated.

Extensive Reading (ER) is recognized for enhancing English proficiency in EFL learners. Although understanding speed is essential for analyzing reading behavior, limited research has focused specifically on reading speed during ER sessions. This study addresses this issue by analyzing log data from junior high school students engaged in ER activities. Using agglomerative hierarchical clustering, we identified four distinct reading profiles based on Word Per Minute (WPM) changes. Future studies should further explore the impact of these profiles on the effectiveness of ER.

Learning EFL through translation tasks is an effective language learning technique, but requires consistent practice and scaffolding. This study evaluates TAMMY, a prototype EFL chatbot designed for Japanese learners to practise English translation tasks. Using the extended Technology Acceptance Model, the study examines Tammy's usability, usefulness, and enjoyment. Response appropriateness and task success are also explored. Findings from a pilot study with Japanese university students indicate high usability and positive attitudes towards the chatbot. Tammy effectively provided accurate feedback in most tasks successfully guiding learners to an accurate translation, though improvements are needed in feedback clarity and conversational adaptability. Despite limitations, Tammy shows promise as a support tool for language learning, offering an engaging and non-judgmental platform for practising translation and enhancing English proficiency.

This study aims at modeling and visualizing students' behavior in a self- regulated and unguided learning environment with a focus on learning progression. Since the modeling approach is process-oriented and does not depend on specific mastery learning criteria, this paper provides a novel way to identify wheel-spinning in self-regulated learning solely based on activity monitoring. The study investigates the free and unsupervised engagement of junior high school students in solving mathematics exercises during summer vacation. During this period, a pool of exercises was provided on the LEAF online learning platform. Additionally, the students receive adaptive exercise recommendations as an add-on. Guided by the basic idea of wheel- spinning as persistent engagement without learning progression, we have designed a mathematical model and a graphical representation to capture and gauge the individual learning progression. Based on an expert questionnaire survey, we considered how this novel representation can serve as a basis to analytically characterize learning progression and specifically to identify wheel-spinning.

Providing explanations in educational recommender systems are supposed to increase students’ awareness of the recommendations, trust toward the system, motivation to adopt the recommendations. With the expectation to have a higher prediction accuracy, more and more complex recommendation models are developed, which are difficult to explain. It remains debatable that whether there exists a trade-off between the accuracy and explainability of recommender systems. In this study, we focus on the explainable math quiz recommender system--- Naïve Concept Explicit (Naïve CE) proposed in our previous work. We are interested in knowing whether the explainable Naïve CE has a good prediction accuracy compared with a powerful but less explainable model--- Matrix Factorization (MF). We also proposed a combined model CE+MF to preserve the explainability of Naïve CE and predicting power of MF. We then used a long-term quiz answering dataset to evaluate the models’ accuracy as to predicting students’ correctness rate of the quizzes. The results revealed that 1) The explainable model Naïve CE had a lower accuracy than the less model MF given the sparse dataset; 2) Combining two models achieved a moderate accuracy in predicting students’ answers while preserving the explainability of Naïve CE. Our study served as an example of how to develop an inherently explainable educational recommender system and how to improve the accuracy by integrating more complex models.

Explainable recommendations, which provide explanations about why an item is recommended, help to improve the transparency, persuasiveness, and trustworthiness. However, few research in educational technology utilize explainable recommendations. We developed an explanation generator using the parameters from Bayesian knowledge tracing models. We used this educational explainable recommendation system to investigate the effects of explanation on the summer vacation assignment for high school students. Comparing the click counts of recommended quizzes with and without explanations, we found that the number of clicks was significantly higher for quizzes with explanations. Furthermore, system usage pattern mining revealed that students can be divided to three clusters— none, steady and late users. In the cluster of steady users, recommended quizzes with explanations were continuously used. These results suggest the effectiveness of an explainable recommendation system in the field of education.

Adapting learning experience according to the rapidly-changing job market is essential for students to achieve fruitful learning and successful career development. As building blocks of potential job opportunities, we focus on “technical terminologies” which are frequently required in the job market. Given a technical terminology, we aim at identifying an order of courses which contributes to the acquisition of knowledge about the terminology and also follows the prerequisite relationships among courses. To solve the course ordering problem, we develop a two-step approach, in which course-terminology relatedness is first estimated and then courses are ordered based on the prerequisite relationships and the estimated relatedness. Focusing on the second step, we propose a method based on Markov decision process (MDPOrd) and compare it with three other methods: (1) a method that orders courses based on aggregated relatedness (AggRelOrd), (2) a method that topologically sorts the courses based on personalized PageRank values (PageRankTS), and (3) a method that greedily picks courses based on the average relatedness (GVPickings). In addition to evaluating how the order prioritizes the related courses, we also evaluate from pedagogical perspectives, namely, how the order prioritizes specifically/generally fundamental courses, and how it places courses close to their prerequisites. Experimental results on two course sets show that MDPOrd outperforms the other methods in prioritizing related courses. In addition, MDPOrd is effective in ordering courses close to their prerequisites, but does not work well in highly ranking fundamental courses in the order.