personalized-learning
Filtering by topic personalized-learning(5)Clear all filters
- PaperOpenAlex — TESOL research22 Jul 2026
THE TRANSFORMATIVE ROLE OF ARTIFICIAL INTELLIGENCE IN ENGLISH LANGUAGE TEACHING
Madaminova, Nargizaxon Jahongir qizi,
The integration of artificial intelligence (AI) into English Language Teaching (ELT) is prompting a reevaluation of curriculum development, learner assessment, and teacher responsibilities. A thematic analysis reveals a shift toward personalized learning and data-informed curricula, suggesting AI will redefine teachers' roles and learning objectives rather than replace traditional instruction.
Original abstract
The integration of artificial intelligence (AI) into English Language Teaching (ELT) signifiesa critical evolution in both pedagogical practice and instructional design. As AI technologiesrapidly develop and become widely accessible, educators and researchers are reevaluating thefoundational components of language instruction, including curriculum development, learnerassessment, teacher responsibilities, and communicative goals. This article explores themedium-term implications of AI in ELT, identifying key challenges and opportunities arisingfrom its implementation. A thematic analysis of current discourse in the field reveals a shifttoward personalized learning, data-informed curricula, and the need for new literacies amongboth teachers and learners. The findings suggest that AI will not replace traditional instructionbut rather redefine the teacher's role and reshape learning objectives.
- PaperComputers and Education: Artificial Intelligence11 Jul 2026
Fair and explainable educational recommendations with a hybrid Graph-GRU framework
Edmund Evangelista, Syed M. Salman Bukhari
A Hybrid Heterogeneous Knowledge Graph-Gated Recurrent Unit framework is introduced to make educational recommendations more fair, robust, diverse, and explainable. The approach combines graph embeddings with sequential modeling, incorporating multi-objective training, reranking, and model-centric explainability. Evaluation on a Moodle dataset shows strong predictive performance (HR@10=0.68, MRR=0.41) but reveals persistent popularity bias.
Original abstract
Artificial Intelligence (AI) recommender systems are increasingly used in education to personalize learning and help students navigate large collections of digital learning resources. However, many existing approaches emphasize predictive accuracy over fairness, robustness, diversity, and transparency. This creates an important educational challenge. The students with limited participation histories may receive less reliable support, while highly popular resources may dominate recommendation lists and limit access to other useful learning materials. To address this challenge, this study aims to develop and evaluate a responsible educational recommender framework that supports personalized learning resource navigation while making recommendation behaviour more fair, stable, diverse, and explainable. This study introduces the Hybrid Heterogeneous Knowledge Graph-Gated Recurrent Unit (Hybrid HKG-GRU) framework, which combines heterogeneous graph embeddings with sequential modelling to capture both the relational structure of course materials and the temporal dynamics of learner interactions. The framework integrates three contributions: (i) multi-objective training with Group Distributionally Robust Optimization (GroupDRO), (ii) Maximum Marginal Relevance (MMR) reranking to reshape exposure patterns, and (iii) built-in, model-centric explainability through path-based and counterfactual analyses. The empirical evaluation shows strong predictive performance with HR@10 = 0.68 and MRR = 0.41 on Moodle LMS logs dataset that comprises of 152 students, 59 resources, and approximately 150k interactions. The model also achieves high intra-list diversity and moderate catalogue coverage, while showing moderate counterfactual stability for many learners (median CR@10 = 1.0), although catalogue-level popularity bias remains evident. The framework provides model-centric interpretability and verification intended to support more transparent educational recommendation. The study positions the framework as a technically auditable approach for improving how learning resources are recommended, inspected, and monitored in educational settings. By integrating fairness, robustness, and explainability as coequal design objectives, the Hybrid HKG-GRU provides a methodological foundation for more responsible and accountable recommender systems in education and related high-stakes contexts.
- PaperETS Research Report Series29 Jun 2026
An Approach for Personalizing Accommodations in Digital Content Assessments for Multilingual Learners
Alexis López, Lin Gu, Diego Zapata-Rivera
Proposes a practical approach for personalizing accommodations for multilingual learners in digital content assessments, including specific actions before, during, and after the assessment. Outlines a sample use case and the empirical evidence needed to validate the approach.
Original abstract
In this research memorandum, we propose a practical approach for personalizing accommodations for multilingual learners in digital content assessments (e.g., mathematics, science). We begin by providing background information about multilingual learners in U.S. public schools and the accommodations commonly used in content assessments. Next, we describe our personalized approach to assigning accommodations to multilingual learners, which we believe is not only effective but also feasible to implement. This approach includes specific actions before, during, and after the assessment. We then provide a sample use case to illustrate how this approach works in practice. Finally, we outline the empirical evidence needed to validate this approach, further supporting its effectiveness.Suggested citation: López, A. A., Gu, L., & Zapata-Rivera, D. (2026). An approach for personalizing accommodations in digital content assessments for multilingual learners (Research Memorandum No. RM–26-05). ETS. https://doi.org/10.64634/and9sy26
- PaperComputers and Education: Artificial Intelligence6 Jun 2026
Personalized neural cognitive architecture search: AutoML-driven diagnostic model generation for heterogeneous learner profiles
Liyuan Jia, Ke Dong
A personalized neural cognitive architecture search framework driven by automated machine learning integrates multi-modal educational data to construct dynamic learner profiles, combining differentiable search strategies with Bayesian performance prediction to automatically identify optimal diagnostic model structures. Evaluated on 28.45 million educational records, the method achieves an AUC of 89.1%, accuracy of 85.3%, and F1-score of 84.7%, outperforming traditional psychometric approaches and mainstream deep learning baselines.
Original abstract
With the rapid advancement of digital transformation in education, personalized learning has become a central objective for improving educational quality. However, traditional educational models struggle to effectively process multi-source heterogeneous learning behavior data, resulting in limited learner profiling and inefficient diagnostic model development. In addition, existing teaching quality evaluation systems mainly rely on static examination outcomes and simple statistical indicators, lacking the capability to dynamically analyze learning processes. To address these challenges, this study proposes a personalized neural cognitive architecture search framework driven by automated machine learning. The framework integrates multi-modal educational data using heterogeneous information network technology to construct dynamic learner profiles incorporating cognitive states, behavioral sequences, and contextual factors. A hierarchical neural architecture search space is then designed, combining differentiable search strategies with a Bayesian performance predictor to automatically identify optimal diagnostic model structures. Experimental results based on 28.45 million educational records show that the proposed method achieves an AUC of 89.1%, accuracy of 85.3%, and F1-score of 84.7%. The model significantly outperforms traditional psychometric approaches and surpasses mainstream deep learning and AutoML baselines. Ablation experiments further confirm the importance of multi-source data fusion and automated architecture search. Despite strong performance, challenges remain regarding computational efficiency and fairness validation across diverse learner populations.
- PaperDOAJ — Language assessment1 Jun 2026
Robust English Knowledge Tracing via Profile-Driven Forgetting and Masked Consistency
Xibo Chen, Ziqi Zhang, Haize Hu, Jie Jin et al.
Proposes a robust English knowledge tracing framework with profile-driven adaptive forgetting and masked consistency regularization. The approach captures individualized memory retention patterns in language learning and mitigates overfitting to noisy assessment data. Experiments show significant improvements in prediction accuracy and noise resistance over existing models.
Original abstract
Knowledge Tracing (KT) plays a pivotal role in Intelligent Tutoring Systems (ITS) by dynamically assessing learners’ evolving knowledge states. However, tracking the acquisition of English presents unique challenges. Existing KT models typically employ homogeneous, predefined forgetting mechanisms that fail to capture the highly individualized nature of linguistic memory retention. Furthermore, language assessment data is notoriously noisy, which leads models to overfit superficial performance rather than capturing true underlying linguistic competence. To address these issues, we propose a novel framework to robustly trace English language competence. First, we introduce a Learning-Profile-Driven Adaptive Forgetting mechanism. Unlike methods with shared forgetting rates, our approach constructs a dynamic and strictly causal profile from historical interactions to generate personalized cognitive parameters (e.g., individualized forgetting rates). These parameters synchronously modulate the decay of multi-level knowledge states, enabling the model to accurately capture the heterogeneous memory retention patterns of different learners. Second, we design a Masked Consistency Regularization training paradigm. By applying stochastic masking to historical responses and enforcing predictive consistency, we prevent the model from exploiting localized noise and “shortcut” learning, compelling it to mine robust and invariant language representations. Extensive experiments on real-world educational datasets demonstrate that our proposed framework significantly outperforms state-of-the-art baselines in both prediction accuracy and noise resistance, offering a robust and interpretable solution for personalized language learning.