学习分析：从源起到实践与研究

学习分析是“大数据”在教育领域的应用,引发了教育技术发展的第三次浪潮,并获得学术界的广泛关注。本文梳理了学习分析的形成过程,然后从利益相关者、研究目标、研究对象、技术方法四个维度,回顾了近五年来国内外学者在学习分析方面的研究成果,并提出未来发展趋势和可能遇到的挑战,便于相关人员制定教育决策、优化教育管理过程以及完善学习过程。研究结果表明,学习分析研究主题主要涵盖学习者知识建模、学习情绪建模、学习行为特征抽取、学习活动跟踪、学习者建模、学位获取分析、教学资源和教学策略优化、自适应学习系统和个性化学习、在线学习影响因素分析九个方面;分析数据主要来源于集中式学习环境、分布式学习环境以及身体活动数据;常用分析方法包括统计分析、信息可视化、数据挖掘、社会网络分析、话语分析和网站分析。目前,学习分析研究遇到的挑战包括教育数据预处理难度大、数据访问权限不明确、学习分析适用性有限。虽然学习分析尚处于发展初期,但由于能够为教育系统各级决策提供科学参考,已经成为教育信息化的重要内容之一。     

大数据时代学习分析与高职院校教育改革

面对来势汹涌的大数据时代,如何有效度量、发现、评估与操纵信息化学习管理系统中积累的海量数据,已成为未来高职院校教育改革过程中不可回避的棘手问题。学习分析是大数据时代高职院校教育改革的助推器,是解决这一现实问题的有效途径之一。从高职院校教育改革在大数据时代所遭遇的挑战出发,阐述学习分析技术对高职院校教育改革的推动作用,并从高职院校教育管理、教师教学与学生学习三个方面分析学习分析技术对高职院校教育改革的影响。     

学习分析技术的发展和挑战——第四届学习分析与知识国际会议评析

第四届学习分析与知识国际会议于2014年3月24-28日在美国印第安纳州波利斯成功举行,会议以探讨学习分析研究、理论和实践的交叉点为主题,涵盖了学习分析技术在教育学、教育心理学、教育管理学、工程学中的运用,以及教育数据挖掘、计算机算法和数据可视化等方面的发展。文章首先说明了此次会议的背景,从研究、理论和实践三方面阐析学习分析主题之间的关系,简述了来自孟菲斯大学的格莱赛教授(Art Graesser)、香港大学的罗陆慧英(Nancy Law)教授和加州大学圣地亚哥分校的克莱默教授(Scott Klemmer)三位专家所作的主题报告;然后从学习分析与课程教学设计、教与学过程挖掘和评价、学习分析与学习资源、文本挖掘与语义分析、学习分析与数学教育、学习分析与教育一体化、学习分析多元化等七个方面对分论坛报告及会议进行系统综述;文章最后指出未来学习分析研究和发展的五个方向:逐步明晰学习分析系统概念与理论、研究通用性的算法和模型、研制学习分析技术标准、支撑数据驱动的学习和评估、融入教育信息化应用与实践、推进教育的深度发展和加快多元化进程,期望能够推动学习分析系统化研究和在教育中的深度应用。     

学习分析：教育信息化的新浪潮

教育信息化经历了学习管理系统（LMS）以及Web2.0应用的变革。新技术的深入应用带来了教育＂大数据＂的高速增长,挖掘这些教育数据潜在价值的迫切需求,使得学习分析应运而生。通过文献分析法,对国内外学习分析文献进行了分析和综述,首先对学习分析进行了概念界定和历史溯源,比较了与学习分析相关概念的区别和联系,之后针对学习分析作为教育信息化新热点,对其研究、发展、技术策略等方面进行了较系统地阐释,最后总结了学习分析目前面临的挑战和愿景,以期可以对学习分析进行全方位的阐述和梳理,并促进该领域的深入研究。     

大数据视角分析学习变革——美国《通过教育数据挖掘和学习分析促进教与学》报告解读及启示

“数据驱动学校,分析变革教育”的大数据时代已经来临,利用教育数据挖掘技术和学习分析技术,构建教育领域相关模型．探索教育变量之间的相关关系．为教育教学决策提供有效支持将成为未来教育的发展趋势。“大数据”的出现．将掀起人类教与学的又一次变革。2012年,美国国家教育部发布了《通过教育数据挖掘和学习分析促进教与学》报告．对美国国内大数据教育应用领域和案例。以及应用实施所面临的挑战进行了详细的介绍。借鉴此报告．我们认为未来我国教育领域的大数据研究和应用。应加强国家和地方对相关的研究和应用在技术层面、管理体制层面以及法律制度层面的支持,按需合理规划具体研究和应用,整合现有资源,发挥后进优势,借助“大数据”实现真正意义上的个性化学习．进而实现教育公平。     

Netflixing human capital development: personalized learning technology and the corporatization of K-12 education

Abstract

Advanced by powerful venture philanthropies, educational technology companies, and the US Department of Education, a growing movement to apply ‘big data’ through ‘learning analytics’ to create ‘personalized learning’ is currently underway in K-12 education in the United States. While scholars have offered various critiques of the corporate school reform agenda, the role of personalized learning technology in the corporatization of public education has not been extensively examined. Through a content analysis of US Department of Education reports, personalized learning advocacy white papers, and published research monographs, this paper details how big data and adaptive learning systems are functioning to redefine educational policy, teaching, and learning in ways that transfer educational decisions from public school classrooms and teachers to private corporate spaces and authorities. The analysis shows that all three types of documents position education within a reductive set of economic rationalities that emphasize human capital development, the expansion of data-driven instruction and decision-making, and a narrow conception of learning as the acquisition of discrete skills and behavior modification detached from broader social contexts and culturally relevant forms of knowledge and inquiry. The paper concludes by drawing out the contradictions inherent to personalized learning technology and corporatization of schooling. It argues that these contradictions necessitate a broad rethinking of the value and purpose of new educational technology.     

What changes,and for whom? A study of the impact of learning analytics-based process feedback in a large course

Recent developments in educational technologies have provided a viable solution to the challenges associated with scaling personalised feedback to students. However, there is currently little empirical evidence about the impact such scaled feedback has on student learning progress and study behaviour. This paper presents the findings of a study that looked at the impact of a learning analytics (LA)-based feedback system on students' self-regulated learning and academic achievement in a large, first-year undergraduate course. Using the COPES model of self-regulated learning (SRL), we analysed the learning operations of students, by way of log data from the learning management system and e-book, as well as the products of SRL, namely, performance on course assessments, from three years of course offerings. The latest course offering involved an intervention condition that made use of an educational technology to provide LA-based process feedback. Propensity score matching was employed to match a control group to the student cohort enrolled in the latest course offering, creating two equal-sized groups of students who received the feedback (the experimental group) and those who did not (the control group). Growth mixture modelling and mixed between-within ANOVA were also employed to identify differences in the patterns of online self-regulated learning operations over the course of the semester. The results showed that the experimental group showed significantly different patterns in their learning operations and performed better in terms of final grades. Moreover, there was no difference in the effect of feedback on final grades among students with different prior academic achievement scores, indicating that the LA-based feedback deployed in this course is able to support students’ learning, regardless of prior academic standing.     

How do tutors use data to support their students?

ABSTRACT

Despite widespread enthusiasm, evidence of the effectiveness of learning analytics remains mixed. One possible explanation for this is that insufficient attention has been paid to the contexts in which it is introduced. We report here on a small-scale study into the prior use of data and communications technologies by tutors, who comprise a key user group in The Open University’s tuition model. Tutors interviewed reported using a complex set of data sources and information tools, and creating local/personal tools and methods for keeping track of students and their interactions with them.     

近八年我国学习分析研究的热点与趋势分析

以七本国内核心学术期刊在2012-2019年发表的156篇学习分析相关研究文献为研究对象,以共词分析法为研究方法,运用SATI、SPSS、Ucinet等工具对数据进行定量分析和可视化呈现,对近八年我国学习分析研究的热点和趋势进行解读。最后,针对学习分析研究的现状,提出相应的建议,旨在对国内学习分析研究提供参考。     

基于数据挖掘的学生投入模型与学习分析

学生投入是高等教育质量和学习成果的重要影响因素,对于高等教育评估与改革具有积极作用,受到了国内外研究者的广泛关注。文章以构建学生投入模型为基础,采用典型相关分析和数据挖掘方法相结合,识别学生投入的相关因素,并对学生学习行为进行分类研究。分析发现学生投入与学生家庭背景、学生入学前特征、学校特征及课程作业之间存在着显著相关关系,不同的学生投入及其学习行为表现有助于加深学校对学生学习行为的了解,更好地研究学习规律的新趋势,为审视高校以生为本、以学为中心的人才培养措施和多元性发展,提供了重要的参考与支持。