Quantum computing enhanced knowledge tracing: Personalized KT research for mitigating data sparsity

Knowledge tracing (KT) is a research topic that seeks to model the knowledge acquisition of students by analyzing their past performance in answering questions, based on which their performance in answering future questions is predicted. Each question involves a knowledge component (KC) such as the topics concerned or the skills required. However, existing models only consider whether a student answers a question correctly at the end, but not the process of how the student attempts to answer it. It is anticipated that the interaction process can at least partially reveal the thinking process of the student, and hopefully even the competence of acquiring or understanding each of the KCs. By analyzing fine-grained clickstream events recorded for each question, we can better understand the student’s ability and performance or even the learning process, just like a personal tutor observing how a student solves a problem. Based on real student interaction data including clickstream events collected from an online learning platform on which students solve mathematics problems, we conduct clustering analysis for each question to show that clickstreams can reflect students’ behavior such as the steps and order of answering a question, time allocation, and score acquiring ability. We then propose the first clickstream-based KT model, dubbed the Click-stream Knowledge Tracing (CKT) model, which augments a basic KT model by modeling the clickstream activities of students when answering questions. We apply different variants of CKT and compare them with the baseline KT model that does not use clickstream data. Despite the limited number of questions with clickstream data and its noisy nature, which may compromise the data quality, we show that incorporating clickstream data leads to performance improvement. This pilot study will likely open a new direction in KT research by analyzing the finer-grained interaction data of students on online learning platforms.

In order to explore the maturity of online concerts and the digital content of music resources, this article analyzes the role of artificial intelligence in music education, discusses the application of artificial intelligence in music education and the development trend of artificial intelligence in education, and studies the quality of vocal music teaching based on artificial intelligence technology. In this paper, ARM and SA algorithms, as well as internal and external probability algorithms, are combined for research and analysis. Through this study, the authors show that human intelligence skills have a certain impact on vocal music teaching, with an impact rate of 56.42%. It can be seen that artificial intelligence can directly optimize the level of music teachers and promote the improvement of teachers' teaching quality and efficiency. This article improves the effective understanding of artificial intelligence in music education and strengthens the scientific and rational application of artificial intelligence in education.

SGKT: Session graph-based knowledge tracing for student performance prediction

In educational data mining, knowledge tracing (KT) aims to model learning performance based on student knowledge mastery. Deep-learning-based KT models perform remarkably better than traditional KT and have attracted considerable attention. However, most of them lack interpretability, making it challenging to explain why the model performed well in the prediction. In this paper, we propose an interpretable deep KT model, referred to as fuzzy deep knowledge tracing (FDKT) via fuzzy reasoning. Specifically, we formalize continuous scores into several fuzzy scores using the fuzzification module. Then, we input the fuzzy scores into the fuzzy reasoning module (FRM). FRM is designed to deduce the current cognitive ability, based on which the future performance was predicted. FDKT greatly enhanced the intrinsic interpretability of deep-learning-based KT through the interpretation of the deduction of student cognition. Furthermore, it broadened the application of KT to continuous scores. Improved performance with regard to both the advantages of FDKT was demonstrated through comparisons with the state-of-the-art models.

Artificial Intelligence (AI) has rapidly emerged as a transformative force across diverse sectors worldwide, with policy initiatives signalling its rising prominence. In the realm of education, AI holds promise for revolutionising learning and teaching. However, the incorporation of AI in basic education faces significant challenges for many schools, particularly when explicit curriculum guidelines are absent, and teachers have limited exposure to AI technologies. This study delves into the importance of integrating Artificial Intelligence in Education (AIED), particularly in primary and secondary school settings, with a specific emphasis on the obstacles and facilitators. The research examines the impact of digital leadership and its role in mitigating teachers' barriers to AIED incorporations. These external variables are systematically outlined within the conceptual framework proposed by this study. Furthermore, it conceptualises and considers three AIED approaches—Learning from AI, Learning about AI, and Learning with AI—as internal variables central to basic-education AIED incorporations, as highlighted in previous research. The study gathers quantitative data through a self-constructed questionnaire survey from 204 school principals and management-level teachers across 60 primary and secondary schools in Hong Kong, capturing their perceptions of AIED incorporation. A structural equation model (SEM) is adopted to analyse the relationships between digital leadership, internal and external teacher barriers, and the three AIED approaches. The findings underscore that digital leadership is a significant factor in facilitating AI incorporations in schools, and that teachers' internal and external barriers considerably affect Learning about AI. The paper concludes by proposing strategies to enhance the capabilities of school leaders and teachers in promoting AIED in basic education.

Knowledge tracing (KT) is an essential task in online education systems. It aims to predict the future performance of students based on their historical learning interaction data. Despite significant advancements in attention-based KT models, they still face some limitations: inaccurate input representation and excessive student forgetting modeling. These limitations often lead to the attention noise problem: the model assigns non-negligible attention weight to some information that is cognitively irrelevant in nature, thereby generating interference signals. To address this problem, we propose a novel KT model, i.e., DenoiseKT. DenoiseKT effectively models the difficulty of the questions and utilizes graph neural network to capture the complex relationship between questions, thereby refining the representations of input features. Additionally, the denoised attention mechanism introduces a weight factor to reduce the model's attention weight distribution on irrelevant information. We extensively compare DenoiseKT with 22 state-of-the-art KT models on 4 widely-used public datasets. Experimental results show that DenoiseKT can effectively solve the attention noise problem and outperform other models. The source code of DenoiseKT is available at https://pykt.org.

Model-agnostic counterfactual reasoning for identifying and mitigating answer bias in knowledge tracing

Recent advancements in computer-assisted learning systems have caused an increase in the research of knowledge tracing, wherein student performance on coursework exercises is predicted over time. From the viewpoint of data structure, the coursework can be potentially structured as a graph. Incorporating this graph-structured nature into the knowledge tracing model as a relational inductive bias can improve its performance; however, previous methods, such as deep knowledge tracing, did not consider such a latent graph structure. Inspired by the recent successes of the graph neural network (GNN), we herein propose a GNN-based knowledge tracing method, i.e., graph-based knowledge tracing. Casting the knowledge structure as a graph enabled us to reformulate the knowledge tracing task as a time-series node-level classification problem in the GNN. As the knowledge graph structure is not explicitly provided in most cases, we propose various implementations of the graph structure. Empirical validations on two open datasets indicated that our method could potentially improve the prediction of student performance and demonstrated more interpretable predictions compared to those of the previous methods, without the requirement of any additional information.

Meta-path structured graph pre-training for improving knowledge tracing in intelligent tutoring

Knowledge Tracing (KT) refers to the problem of predicting learners’ future potential performance given their past learning history in e-learning systems. In order to better trace the learners’ knowledge, KT tasks have become increasingly complicated recently, and various factors related to learning (such as skill, exercise, hint, etc.) have been incorporated into the modeling of KS of the learner, which renders it inadequate for the traditional KT definition to formalize these tasks. Therefore, this paper first gives a more general formal definition of KT tasks, and then proposes an Extensible Deep Knowledge Tracing model for multiple learning factors based on this general definition, named EDKT. EDKT can integrate various different learning factors by extending or ablating factors in two plug-ins on the basis of minor modifications. To demonstrate the effectiveness of the proposed model, we conduct extensive experiments on three real-world benchmark datasets, and the results show that EDKT comprehensively outperforms the state-of-the-art KT models on predicting future learner responses.

This chapter traces the ethical issues around applying artificial intelligence (AI) in education from the early days of artificial intelligence in education in the 1970s to the current state of this field, including the increasing sophistication of the system interfaces and the rise in data use and misuse. While in the early days most tools were largely learner-facing, now there are tools that are teacher-facing, supporting their management of the classroom, and administrator-facing, assisting in their management of cohorts of students. Learner-facing tools now take into account the affective and motivational aspects of learning as well as the cognitive. The rise of data collection and its associated analytic tools has enabled the development of dashboards for the dynamic management and reflective understanding of learners, teachers, and administrators. Ethical issues hardly figured in the early days of the field but now they loom large. This is because of the legitimate fears that learners’ and teachers’ autonomy will be compromised, that learner data will be collected and potentially misappropriated for other purposes, and that AI will introduce extra biases into educational decisions and increase existing inequity and also because of the scary reputation that AI has in general.

Knowledge tracing aims to trace students’ evolving knowledge states by predicting their future performance on concept-related exercises. Recently, some graph-based models have been developed to incorporate the relationships between exercises to improve knowledge tracing, but only a single type of relationship information is generally explored. In this article, we present a novel Dual Graph Ensemble learning method for Knowledge Tracing (DGEKT), which establishes a dual graph structure of students’ learning interactions to capture the heterogeneous exercise–concept associations and interaction transitions by hypergraph modeling and directed graph modeling, respectively. To combine the dual graph models, we introduce the technique of online knowledge distillation. This choice arises from the observation that, while the knowledge tracing model is designed to predict students’ responses to the exercises related to different concepts, it is optimized merely with respect to the prediction accuracy on a single exercise at each step. With online knowledge distillation, the dual graph models are adaptively combined to form a stronger ensemble teacher model, which provides its predictions on all exercises as extra supervision for better modeling ability. In the experiments, we compare DGEKT against eight knowledge tracing baselines on three benchmark datasets, and the results demonstrate that DGEKT achieves state-of-the-art performance.

This research aims to critically examine the ethical integration of artificial intelligence (AI) in education through the perspective of maqāṣid al-sharīʿah, emphasizing the alignment between technological innovation and Islamic moral principles. The methods used are a systematic literature review and thematic content analysis against peer-reviewed publications for the period 2015–2025, which discuss the application of AI in primary, secondary, and higher education. The study identified dominant ethical issues, such as data privacy, algorithmic bias, accountability, human agency, and moral development, which were then mapped to Islamic ethical goals, including ʿadl (justice), amānah (belief), karāmah al-insān (human dignity), and ḥifẓ al-ʿaql (protection of reason). The results of the analysis show that the adoption of AI in education often emphasizes efficiency, personalization, and predictive analytics, but has the potential to reduce learners' autonomy and ethical reasoning. The mapping of maqāṣid al-sharīʿah shows a strong normative conformity, so that Islamic principles can be a moral foundation as well as a practical guide for AI governance. The research contribution is theoretical by bridging the literature on AI ethics and Islamic educational philosophy, as well as practical by offering an integrative framework for AI policymakers, educators, and developers. The integration of maqāṣid al-sharīʿah in AI governance ensures justice, trust, inclusivity, and the development of the whole human being (insān kāmil).

Knowledge tracing models student exercise records to dynamically assess their knowledge levels, providing targeted guidance for education and learning.Existing knowledge tracing models lack the utilization of global information in question representation and have not overcome the issue of long-term dependency on the sequence of student responses.To address these issues, we propose an Enhanced Question Representation and Historical Performance Fusion Knowledge Tracing model (QRHKT).First, we construct a heterogeneous graph structure by combining the inclusion relations between questions and concepts, transition relations between questions, and co-occurrence relations between concepts, and enhance question representations through graph neural network algorithms.To address the long-term dependency issue, we categorize the knowledge states into current knowledge states and historically important knowledge states from the perspective of the importance of a student's historical knowledge state.The current knowledge state is obtained through a long short-term memory network, and historically important knowledge states are generated by weighted aggregation based on importance coefficients.Finally, by integrating these two types of knowledge states with question representation, we predict the student's answering performance.Experimental results show that our proposed QRHKT achieves better knowledge tracing results on three public datasets.

: The educational system, unlike other social systems, is distinguished at the same time by conservatism, necessary to protect itself from frequent and thoughtless changes as a result of temporary conjunctural moods, and modernism, expressed in the desire to prepare learners for the current needs of society. This duality also gives rise to many arguments for and against the introduction of artificial intelligence (AI) in education - if it does not, the education system will fall behind the realities, if it does, it may compromise its main purpose - to provide validated and verified knowledge to students and the students. The purpose of this article is to examine the possibilities of using AI in universities and to reveal the limitations that hinder it. In this sense, the object of the study is artificial intelligence, and the subject - its application in the higher education system. The purpose of the study is to examine, through a SWOT analysis, the opportunities and threats in the use of AI applications in universities, as well as their strengths and weaknesses, determining their readiness for it. A study has been conducted that shows that the opportunities for using artificial intelligence in education slightly outweigh the threats, and the strengths of universities as a terrain for implementing AI. The analysis also highlights what are the main levers for the development of AI in universities, what are the limitations to it, what are the risks that may occur in the future and what are the problems that can be expected if threats are not overcome and weaknesses are minimized. It is concluded that AI applications can be very useful in the work of teachers, and students want them, but this should be done carefully, respecting certain principles of equality, credibility, ethics and guaranteeing human rights.