读个文献:人工智能重塑个性化学习(AI+Personalized Learning)-夜雨聆风

读个文献:人工智能重塑个性化学习(AI+Personalized Learning)

💡关注我，在专业里精进，在生活中自愈 ~~~

📚 教科研干货 & AI实践 💡 电商教学实践 📖 读书笔记 ☀️ 愈己的「云小暖」 ~~~

检索方法

数据库：Web of Science 核心库

检索式：Topics = “artificial intelligence” + “personalized learning”

检索时间：Year to date

Redefining personalized learning in the artificial intelligence era: an updated systematic review from 2019 to 2025

在人工智能时代重新定义个性化学习：2019–2025年最新系统性综述

📖 Smart Learning Environments | 27 Feb. 2026

人工智能融入教育，正促使人们重新审视“个性化学习”的术语体系及其对教学实践和学习者参与度的影响。个性化学习涵盖多种教学策略，根据学生的个体需求与兴趣量身定制，利用数据与技术提升学习投入度与成功率。不断演变的教育环境要求我们清晰理解人工智能如何支持个性化学习，并与传统方法区分开来。本文概述了个性化学习领域的最新研究文献，着重阐释技术如何重塑个体化学习体验的框架及其有效性。通过对六大数据库中高质量文献的分析，本综述揭示了人工智能如何重新定义个性化学习，从而推动形成更为精准的定义。研究结果强调了个性化学习相关术语在技术语境中的使用现状，并呼吁采用统一术语以提升教育技术实践的清晰度与有效性。

🔗 论文链接https://doi.org/10.1186/s40561-026-00440-6

<summary>📖

The integration of artificial intelligence (AI) in education is prompting a reevaluation of personalized learning terminology and its impact on teaching practices and learner engagement. Personalized learning (PL) involves various instructional strategies tailored to individual student needs and interests, utilizing data and technology to boost engagement and success. The evolving landscape requires a clear understanding of how AI can support personalized learning, distinguishing it from traditional methods. The variability in PL terminology reflects diverse interpretations of AI technologies in education, necessitating a common framework to clarify definitions and practices. This document presents an overview of the latest research literature on personalized learning, highlighting how technology is transforming the framework and effectiveness of individualized learning experiences. By analyzing reputable articles from 6 databases, the review seeks to provide insights into how AI can redefine personalized learning, enabling more precise definitions. The findings emphasize the use of PL terms in technological contexts and call for a unified term to enhance clarity and effectiveness in educational technology practices. Ultimately, the review aims to inform educators and policymakers about precise terms defining personalized learning in the AI context.

An integrative systematic review analysis of research on technology‑enabled personalized learning and self‑regulated learning

技术赋能的个性化学习与自我调节学习研究的整合性系统综述分析

📖 Smart Learning Environments | JAN 15 2026

本研究探讨了整合个性化学习、自我调节学习与技术如何提升学生的学习质量，并满足高等教育不断发展的需求。尽管早期研究往往分别探讨这些领域，本综述考察了它们共同促进学生自主学习能力与学习成果的潜力。采用PRISMA方法进行文献筛选，利用VOSviewer进行数据分析，对2006–2023年发表的112篇Scopus文献进行分析，识别研究趋势、高影响力期刊及新兴方向。定量分析后，进一步对引用量最高的10篇文献进行了系统的定性综合。分析揭示了“学习分析”“自我调节的支架”“学习的技术中介”等关键主题，以及“学习分析”“智慧环境”“智能辅导”等新兴领域。基于上述发现，研究提出了一个利用技术促进自我调节、增强认知策略使用并提升学业成绩的教学框架。

🔗 论文链接https://doi.org/10.1186/s40561-025-00428-8

<summary>📖

This study examined how integrating personalized learning, self-regulated learning, and technology can enhance students‘ learning quality and meet the evolving needs of higher education. While earlier research often explored these areas separately, this review examines their combined potential to enhance learner autonomy and learning outcomes. Using PRISMA for data selection and VOSviewer for data analysis, 112 Scopus-indexed publications (2006–2023) were examined through bibliometric techniques to identify research trends, influential journals, and emerging opportunities. Following the quantitative analysis, a systematic qualitative synthesis was conducted, focusing on the 10 most-cited studies. The analysis revealed key themes such as ’learning analytics‘, ’scaffolding for self-regulation‘, ’technological mediation of learning‘, and emerging areas including ’learning analytics‘, ’smart environments‘, and ’intelligent tutoring‘. Building on these insights, the study proposes a pedagogical framework that leverages technology to promote self-regulation, enhance the use of cognitive strategies, and improve academic performance.

Multi-modal graph neural networks for cross-domain educational recommendation: integrating behavioral analytics and institutional context for personalized learning

面向跨领域教育推荐的多模态图神经网络：融合行为分析与机构背景数据的个性化学习

📖 Smart Learning Environments | APR 1 2026

摘要:教育推荐系统传统上依赖于单一数据集方法，难以捕捉学生学习的复杂、多维特性。本文提出了一种新颖的多模态图神经网络框架，整合异构教育数据源以提供更优质的个性化学习推荐。将EdNet中的行为学习分析与OULAD中的机构背景相结合，构建了大规模跨数据集教育框架。所提出的架构采用图卷积网络进行结构建模、图注意力网络进行动态加权，并引入分层时间组件以捕捉学习动态。新颖的跨模态注意力机制实现行为模式与背景因素之间的知识迁移，而认知负荷感知优化确保了教育适配性推荐。实验评估表明，该方法在推荐准确性和教育有效性方面均有显著提升，能够高精度预测学生的实际学习选择，并通过自适应优化在保持高投入水平的同时大幅减少学习时间

🔗 论文链接https://doi.org/10.1186/s40561-026-00452-2

<summary>📖

Educational recommendation systems have traditionally relied on single-dataset approaches, limiting their ability to capture the complex, multi-faceted nature of student learning. This paper introduces a novel multi-modal graph neural network framework that integrates heterogeneous educational data sources to deliver superior personalized learning recommendations. Our approach combines behavioral learning analytics from EdNet with institutional context from OULAD, creating a large-scale cross-dataset educational framework. The proposed architecture employs Graph Convolutional Networks for structural modeling, Graph Attention Networks for dynamic weighting, and hierarchical temporal components to capture learning dynamics. Novel cross-modal attention mechanisms enable knowledge transfer between behavioral patterns and contextual factors, while cognitive load-aware optimization ensures educationally appropriate recommendations. Comprehensive experimental evaluation demonstrates substantial improvements in recommendation accuracy and educational effectiveness. Individual-level assessment reveals high accuracy in predicting students’ actual learning choices, with superior success rates for recommended learning activities. Cross-dataset transfer learning achieves excellent performance, showing significant improvements over traditional domain adaptation approaches. Beyond performance metrics, our framework delivers tangible educational benefits including substantial reduction in learning time while maintaining high engagement levels through adaptive optimization. The system demonstrates its capability in learning gap identification and targeted remediation, with strong correlations to educational psychology indicators validating pedagogical authenticity.

Individual and group competitive digital gamification in ESL adult classrooms: a systematic review

个体与小组竞争性数字游戏化在ESL成人课堂中的应用：对词汇保持、动机与参与度影响的系统综述

📖 Smart Learning Environments | MAR 18 2026

英语熟练度对ESL学习者的学术与职业前景至关重要，但对成人ESL学习者而言仍是艰巨挑战。游戏化通过提升趣味性有助于弥合差距，但目前尚不明确：面向成人ESL学习者时，个性化（基于个体）与协作式（基于小组）游戏化哪种更有效。本文对2015–2024年间发表的19篇研究进行了系统综述。结果表明，无论个体化还是小组导向的游戏化，均对语言学习、投入及动机产生积极影响：个体化游戏化促进自主性，协作式学习激发社会互动。学习情境似乎是影响策略成效的重要因素，教师需综合考虑自身课堂情境来设计游戏化策略。

🔗 论文链接https://doi.org/10.1186/s40561-026-00447-z

<summary>📖

English language proficiency is essential for academic and career prospects of individuals who speak English as a second language (ESL). Yet, gaining English proficiency is a difficult task for ESL learners, particularly adults who may not have acquired the language in their formative stages. Gamification helps to bridge the gap by making language learning enjoyable. But there is no clear understanding of which strategy works best for ESL adult learners between personalized (individual-based) and collaborative (group-based) gamification. To address this gap, this study presents a systematic synthesis of the literature on gamified vocabulary learning among adult ESL learners. This review included 19 articles published between January 2015 and December 2024. The findings show that gamification, irrespective of whether it is personalized or group-oriented, has beneficial impacts on language learning, engagement, and motivation. Individual-based gamification promotes learner autonomy while collaborative learning encourages social interaction. Both strategies work for the benefit of learners’ academic achievement, motivation, and engagement. Learning contexts seemed to influence the success of these strategies. The findings indicate that teachers have to weigh the contexts of their ESL classrooms in the design of gamification strategies.

The Impact of AI-Based Personalized Learning Systems on the Cognitive Ability Enhancement of Children With Special Needs

基于人工智能的个性化学习系统对有特殊需求儿童认知能力提升的影响

📖 International Journal of Cognitive Informatics and Natural Intelligence | FEB 6 2026

本研究通过一项历时12个月、涉及360名中国有特殊需求儿童的纵向实验，探讨AI个性化学习系统对认知发展的影响。相比传统方法，该系统在注意力、记忆力和问题解决能力方面均有显著提升。AI系统整合多模态数据与自适应算法，在关键脑区诱发了神经可塑性变化（不同障碍类型呈现差异）。结果揭示了系统使用时长与认知获益之间的剂量反应关系，明确了最佳训练阈值。研究支持AI在特殊教育中的潜力，同时指出资源公平性与教师适应性等挑战。

🔗 论文链接https://doi.org/10.4018/IJCINI.397824

<summary>📖

This study explores the impact of artificial intelligence (AI)-based personalized learning systems on the cognitive development of children with special needs in China. Through a 12-month longitudinal experiment involving 360 participants, the research demonstrates significant improvements in attention, memory, and problem-solving skills compared to traditional methods. The AI system, integrating multimodal data and adaptive algorithms, induced neuroplastic changes in key brain regions, with disorder-specific variations. Results revealed a dose-response relationship between system usage and cognitive gains, highlighting optimal training thresholds. The findings support AI‘s potential in special education while addressing challenges like resource equity and teacher adaptability. The study provides empirical evidence for optimizing AI-driven interventions to enhance learning outcomes for children with cognitive disabilities.

Artificial intelligence in education: a systematic review of personalized learning trends and future directions

教育中的人工智能：个性化学习趋势与未来方向的系统综述

📖 Frontiers in Education |MAR 13 2026

本研究采用PRISMA综述流程及元文献分析方法，对2013–2025年Scopus数据库相关文献进行分析，考察了人工智能与个性化学习在教育领域融合的进展与不足。全球研究重点正从中国、美国和欧洲等主导区域向更广泛的亚洲地区转移，带来新的教育改进机遇。然而，人工智能的快速扩张，加上发展中国家对教育质量的持续担忧，可能产生额外体制性压力，从而影响教育成效。研究对教育工作者、学术机构和政策制定者具有重要启示：专业发展不应仅限于技术熟练度，更应强调教学整合与数字素养；同时，政策制定者需构建伦理框架，应对数据隐私、算法偏见及获取机会不均等关键问题。

🔗 论文链接https://doi.org/10.3389/feduc.2026.1782626

<summary>📖

Purpose: The objective of this research is to compile a thorough review of existing literature, highlighting how artificial intelligence and personalized learning have shaped emerging research opportunities. Research methodology: This study employs the PRISMA review protocol alongside a meta-literature review to analyze pertinent works sourced from the Scopus database, spanning the years 2013 to 2025. Findings: The study examines the progress and deficiencies in the integration of artificial intelligence and personalized learning in education. It underscores a transition in global research priorities from dominant regions such as China, USA and Europe to broader Asia, signaling new opportunities for educational improvement. However, the findings reveal that the swift expansion of AI, combined with persistent concerns about educational standards in developing countries, may create additional institutional pressures that influence the effectiveness of education. Implications: The findings from this review present significant implications for research, practice, and policy. For educators and academic institutions, the results highlight the necessity of professional development that goes beyond technical proficiency, emphasizing pedagogical integration and digital literacy. Furthermore, policymakers are urged to develop ethical frameworks for AI implementation in education, addressing critical issues such as data privacy, algorithmic bias, and unequal access.

Artificial intelligence as a catalyst for self-directed learning in an open and distance e-learning (ODeL) university in South Africa

人工智能作为南非开放与远程电子学习大学中自我导向学习的催化剂

📖 South African Journal of Education | FEB 6 2026

本研究探讨了人工智能如何在一所南非开放与远程电子学习大学中促进自我导向学习。采用定性研究方法，对4位学者进行半结构化访谈，并与10名四年级教育学士学生进行一次虚拟焦点小组讨论。结果表明，AI通过提供个性化反馈、提高参与度以及提升语言习得和自我评估等技能，增强了ODeL环境中的自我导向学习。然而，对AI的过度依赖风险、学术不端行为以及AI生成内容的不准确性等问题，要求实施过程中保持谨慎。研究强调，AI应作为辅助资源而非教育者的替代品。

🔗 论文链接https://doi.org/10.15700/saje.v45ns1a2675

<summary>📖

In this study I explored how artificial intelligence (AI) can foster self-directed learning (SDL) in an open and distance e-learning (ODeL) university in South Africa. In accompanying rapid technological progress, AI provides opportunities for personalised learning, adaptive feedback and independent learning experiences. I adopted a qualitative research approach, conducted semi-structured interviews with 4 academics, and held a virtual focus group discussion with 10 fourth-year B.Ed. students who had been purposively sampled from a South African ODeL university. Data were analysed through thematic analysis. The findings reveal that AI enhances SDL in ODeL environments by providing personalised feedback, increasing engagement, and improving skills such as language acquisition and self-evaluation. However, concerns such as the risk of over-dependence on AI, instances of academic dishonesty and inaccuracies of AI-produced content necessitate a cautious approach to its implementation. The research emphasises that AI should be used as a supplementary resource rather than a replacement for educators. It serves as a tool to enrich learning experiences, although we should address its potential drawbacks to ensure fair and effective use in ODeL contexts.

Enhancing personalized learning with Artificial Intelligence and analytics: university staff’s insights

借助人工智能与分析技术增强个性化学习：大学教职员工的见解

📖 Interactive Learning Environments | JAN 30 2026

大数据与人工智能主导教育研究讨论，但关于它们如何有效支持高等教育中个性化学习的关注有限。本研究探讨了塞浦路斯共和国大学教职员工在AI与学习分析方面的经验。采用解释性序贯混合方法设计，通过45份问卷和两次焦点小组收集数据，汇集了设计及实施技术增强学习的相关人员中鲜少被听到的声音。结果表明，教职员工将个性化视为以学生为中心、根据学习者需求调整教学的过程。学习分析利用绩效指标和行为模式提供参与度洞察，AI则支持任务自动化与教学材料设计，让教职员工能维持更深层次的学习者互动，提升透明度、参与度及自主性。然而，工具不完善、机构支持有限、培训缺口以及对变革的阻力阻碍了实施。研究提出了一个双层路线图，将战略行动与学习设计相结合，以指导AI与学习分析在教学中的整合。

🔗 论文链接https://doi.org/10.1080/10494820.2026.2619907

<summary>📖

Big data and artificial intelligence (AI) dominate educational research discussions. Yet, limited attention is given to how these technologies effectively support personalized learning in higher education. Recognizing that user perceptions influence adoption, this study explores university staff experiences with AI and learning analytics in the Republic of Cyprus, a context rarely examined. Employing an explanatory sequential mixed methods design, data were collected via forty-five questionnaires and two focus groups, gathering the underrepresented voices of all those involved in designing and implementing technology-enhanced learning. Findings indicate that staff view personalization as adapting instruction to learner needs, guided by student-centered pedagogical aims. Using performance indicators and behavioral patterns, learning analytics provides engagement insights, while AI supports task automation and teaching material design. This allows staff to maintain deeper learner interaction and support, promoting transparency, learner engagement and autonomy. However, inadequate tools, limited institutional support, training gaps, and resistance to change hinder implementation. These barriers emphasize the need for capacity building, infrastructure, and professional development. The study’s key contribution is a two-tiered roadmap combining strategic actions and learning design to guide integration of AI and learning analytics in teaching. Despite sampling limitations, these findings offer valuable insights for advancing personalized learning.

Generative AI in work-integrated learning: Supporting pre-service teachers’ emotional labour and self-management in Australian initial teacher education

生成式AI在工学结合学习中的应用：支持澳大利亚职前教师的情绪劳动与自我管理

📖 期刊类别：EDUCATION & EDUCATIONAL RESEARCH | Q1区

本研究探讨了生成式人工智能如何与职前教师在工学结合实习中的情绪劳动、关系复杂性及机构适应经验相互作用。基于“教育中的情绪资本”框架，研究考察了情绪资本在不同情感经济中的保存、转换与消耗过程，以及GenAI活动如何在此过程中作为文化响应的支架。通过对一项干预性职前教师教育案例研究中126名职前教师的调查和焦点小组数据进行分析，发现GenAI活动与情绪自我调节的演练、教学准备及专业信心相关，尤其是在情感模糊或文化不适配的实习环境中。但这些收益并不均衡，受到机构认可、导师态度及文化清晰度的影响。本研究揭示了通过定制化、支架式使用GenAI，可以帮助职前教师在符合学科期望和多元文化情感需求的方式下积累实习所需的情绪资本，并为未来在教师教育中同时关注情感与认知支架的设计提供了方向。

实践要点:已知：GenAI在教育环境中具有提升效率的潜力；职前教师在工学结合实习中面临较高情绪劳动、身份压力及情感误认问题。新增：展示了GenAI如何在实习中为情绪调节、关系信心和文化适应提供支架；揭示了情绪资本如何因实习的情感经济而差异化地被认可或阻碍；将GenAI作为一种文化响应支架，帮助职前教师模拟反馈、预演回应并减少情感孤立。实践/政策启示：教师教育项目应嵌入具有情感智能和伦理意识的AI素养培训；导师教师发展应包含情绪资本与文化情感误认的培训；大学与实习学校的情感期望需要对齐，将GenAI视为实习中情绪合法性的中介者。

<summary>📖

This study investigates how generative artificial intelligence (gen-AI) interacts with pre-service teachers’ (PSTs) experiences of emotional labour, relational complexity and institutional navigation during work-integrated learning (WIL) placements. Using the Emotional Capital in Education (ECE) framework, the study explores how emotional capital is preserved, converted and depleted across diverse affective economies, and how gen-AI activities were taken up as culturally responsive scaffolds in this process. Drawing on survey and focus group data from 126 PSTs in an interventional initial teacher education (ITE) case study, the findings show that gen-AI activities were associated with rehearsal of emotional self-regulation, pedagogical preparation and professional confidence, particularly in emotionally ambiguous or culturally misaligned placements. These benefits, however, were uneven and shaped by institutional recognition, mentor attitudes and cultural legibility. The study contributes by showing how tailored, scaffolded use of gen-AI can help PSTs build emotional capital for placement in ways that align with disciplinary expectations and diverse cultural-emotional needs, pointing to future designs that foreground emotional as well as cognitive scaffolding in ITE.Practitioner notes What is already known about this topic Gen-AI has demonstrated potential to enhance efficiency and productivity in educationsettings. PSTs experience high levels of emotional labour, identity stress and institutional pressure during WIL. Emotional misrecognition and affective mismatch are common among culturally diverse PSTs. What this paper adds Shows how gen-AI can scaffold emotional regulation, relational confidence and cultural navigation for PSTs during WIL. Demonstrates how emotional capital is differentially recognised or blocked depending on the affective economy of the placement. Introduces gen-AI as a culturally responsive scaffold that helps PSTs simulate feedback, rehearse responses and reduce affective isolation. Emphasises the role of AI literacy not just as a technical skill, but as an affective and ethical practice that shapes professional identity. Implications for practice and/or policy ITE programmes should embed emotionallyintelligent, ethically attuned AI literacy training that addresses cultural norms of affect and professionalism. Mentor teacher development should include training on emotional capital and cultural-affective misrecognition to better support diverse PSTs. Institutional policies should align university and school affective expectations, recognising gen-AI not only as a tool but as a mediator of emotional legitimacy in WIL.