多模态学习分析:理解与评价真实学习的新路向

随着物联网、可穿戴传感设备、人工智能的快速发展,多种模态数据的连续抓取与融合分析成为可能,促成了多模态学习分析研究的诞生,并成为学习分析领域的一个重要新兴分支.多模态学习分析关注真实的学习情境与本真的学习交流方式,"返璞归真"地聚焦更普遍的物理学习情境,克服了主流学习分析过度关注数字化学习环境的局限.研究主要采用文献归纳法,阐述了多模态学习分析的发展动因、概念理解,重点从身体、生理视角概述了多模态的数据类型,并对多模态学习分析的过程模型进行了详细描述.研究认为,未来要充分借助人工智能处理多模态数据,借鉴认知带理论融合不同模态数据的意义,借力学习理论来理解真实的多模态学习交互过程,以进一步完善基于多模态数据的学习评价方法.     

Programming Pluralism: Using Learning Analytics to Detect Patterns in the Learning of Computer Programming

New high-frequency, automated data collection and analysis algorithms could offer new insights into complex learning processes, especially for tasks in which students have opportunities to generate unique open-ended artifacts such as computer programs. These approaches should be particularly useful because the need for scalable project-based and student-centered learning is growing considerably. In this article, we present studies focused on how students learn computer programming, based on data drawn from 154,000 code snapshots of computer programs under development by approximately 370 students enrolled in an introductory undergraduate programming course. We use methods from machine learning to discover patterns in the data and try to predict final exam grades. We begin with a set of exploratory experiments that use fully automated techniques to investigate how much students change their programming behavior throughout all assignments in the course. The results show that students’ change in programming patterns is only weakly predictive of course performance. We subsequently hone in on 1 single assignment, trying to map students’ learning process and trajectories and automatically identify productive and unproductive (sink) states within these trajectories. Results show that our process-based metric has better predictive power for final exams than the midterm grades. We conclude with recommendations about the use of such methods for assessment, real-time feedback, and course improvement.     

Learning Fractions by Splitting: Using Learning Analytics to Illuminate the Development of Mathematical Understanding

The struggle with fraction learning in kindergarten through Grade 12 in the United States is a persistent problem and one of the major stumbling blocks to succeeding in higher mathematics. Research into this problem has identified several areas where students commonly struggle with fractions. While there are many theories of fraction learning, none of the research on these theories employs samples large enough to test theories at scale or nuanced enough to demonstrate how learning unfolds over time during instructional activities based on these theories. The work reported here uses learning analytics methods with fine-grained log data from an online fraction game to unpack how splitting (i.e. partitioning a whole into equal-sized parts) impacts learning. Study 1 demonstrated that playing the game significantly improved students’ fraction understanding. In addition, a cluster analysis suggested that exploring splitting was beneficial. Study 2 replicated the learning results, and a cluster analysis showed that compared to early game play, later game play showed more optimal splitting strategies. In addition, in looking at the types of transitions that were possible between a student’s early cluster categorization and later cluster categorization, we found that some types of transitions were more beneficial for learning than others.     

Applying Learning Analytics to the Scholarship of Teaching and Learning

In this article we report on the findings of a project funded by the Australian Office for Learning and Teaching and entitled “Learning Analytics: Assisting Universities with Student Retention.” While this project was primarily focused on retention as a potential outcome of learning analytics, its application could be related to the broader concept of student success. Student success allows for a focus on pedagogy and the use of learning analytics for the improvement of learning and teaching with a firm scholarly evidence base. The data gathered for the project provide the background for a discussion about the potential of learning analytics to inform the practice of the Scholarship of Teaching and Learning. A case study demonstrates the potential of this approach. Overall, clear pedagogical questions are important in the application of learning analytics to the Scholarship of Teaching and Learning, and we suggest potential ways to explore pedagogical questions with big data methods.     

Pathways to Learning

Despite the C.S.W.E. policy statement requirement to integrate content on special populations into the curriculum, many social work educators lack effective teaching methods to meet this mandate. As a result, students struggle with a gap between classroom experience and field demands. Experiential exercises, when incorporated into the practice curriculum, aid in bridging the gap while sensitizing students to the many needs of special populations.     

Using Comparisons of Multiage Learning Environments to Understand Two Teachers' Democratic Educational Aims

Learning Environments Research - Several decades of research detail the nature and the relevance of learning environments in the education of children. This inquiry builds upon this earlier work...     

如何理解“深度学习”

深度学习是落实核心素养的重要途径,是信息时代对知识教学的反思和改进。对于深度学习,应从深度学习的性质、内容、过程以及任务与目的等方面去理解。深度学习不是自学,而是在教师的帮助和带领下学生主体的主动活动。深度学习的内容主要是有挑战性的学习单元,深度学习的过程是学生作为主体的主动学习过程。从根本上来看,深度学习不是一种教学模式,而是一种教学理念;它是历史上一切优秀教学理论与实践的凝炼、提升,是良好教学的理想形态。深度学习的目的是培养能够创造美好未来的社会历史实践的主人。     

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。     

Using API Data to Understand Learning in League of Legends: A Mixed Methods Study

This mixed-methods research was conducted to understand the impact of learning and player growth in a League of Legends summer camp. Eighteen adolescents engaged in a three-day sleep-over summer camp with various team building activities. Data collected included API metadata from pre- and post-camp as well as semi-structured interview data with youth who attended the camp. Exposing the participants to teamwork methods had a significant impact on changing how players approached competitive game play and engagement in digital environments. In particular, we find that participation in the summer camp led to significant changes in vision score, the most team-focused aspect of the game for which statistics were available. Furthermore, as demonstrated by the qualitative data, evidence suggests youth have an understanding for how teamwork can positively influence peer interactions within digital environments. These findings are important as they demonstrate that teaching team-focused activities can have a significant impact on the players of competitive esports games, and it also implies that the role of teamwork within various digital platforms needs deeper study. Findings indicate that a transfer of learning occurs between physical and digital spaces and that youth recognize the importance of teamwork and team-building activities in digital learning spaces.     

学习分析技术:服务学习过程设计和优化

在数据以爆炸式速度递增的信息时代,海量数据给商业发展和科学研究带来了新的契机。在教育领域,智慧学习环境使得积累更加大量、丰富和复杂的教育数据成为可能。如何更加充分、有效地利用这些数据优化教与学成为一个焦点问题。因此,作为一种新兴的技术,学习分析受到越来越多的关注。本文系统地梳理了学习分析的五个环节,介绍和分析了多数据源的数据采集与语义存储的研究进展与挑战,概括了五种典型的数据分析,并阐述了面向不同受众的绩效评估、过程预测与活动干预三种应用服务。     

新手职场学习的内容初探

刚入职的新手在职场中需要学习什么,对这一问题还缺少系统的研究。研究发现,新手职场学习的内容包括工作知识、工作能力与技能、自我概念、团队合作与适应组织文化的能力、负面的经验或认知等。     

Using Analogy to Help Young Children Understand

Analogies offer conceptual models for supporting the development of understanding. Contrary to some expectations, there is growing evidence that young children can reason analogically. Much of this evidence comes from experiments intended to test psychological theories. This study aimed to gauge the practical potential of analogy in topics often considered by teachers difficult for young children to understand. Aspects of young children's understanding of current electricity were compared in two conditions, namely with and without an analogy (87 and 89 children, respectively; 6‐7 years of age). The results indicated that the analogy was of practical value in teaching for understanding. It is suggested that their bases be carefully prepared prior to teaching the target topic and that what is to be understood is modelled directly and is explicitly related to its equivalent in the topic. Further investigations to determine conditions for the effective use of analogies when teaching young children, who benefits particularly and in what ways seem warranted.     

学习分析对自我调节学习的影响机理研究

近年来,众多学者将学习分析应用于自我调节学习以优化学习过程和学习效果,但当前学习分析的应用多以数据为驱动,尚未涉及学习者内在要素的变化规律,无法得知学习分析是如何影响自我调节学习的。为回答该问题,研究首先基于现有研究和理论归纳学习分析与自我调节学习的内在联系。其次,以学习分析的普遍应用模式为背景,收集学习者自我调节学习后的反思和访谈数据,利用认知网络分析和语义分析挖掘自我调节学习受学习分析影响的要素变化规律和各阶段触发特征。最后,总结变化规律和触发特征得到学习分析对自我调节学习的影响机理。结果表明,学习分析介入后,切实促进了自我调节学习各要素的融合,且在自我调节学习的不同阶段,学习分析触发自我调节学习发生的起点和路径存在差异。研究结论为促进学习分析更深入地支持自我调节学习提供了发展方向和理论依据。     

结构分析法在物理教材分析中的运用

介绍了物理教学中的结构分析法的内容及方法,并运用结构分析法对初中物理“力”这一章教材进行了分析与研究。     

自我调节学习中学习分析的应用框架和融合路径研究

为厘清学习分析在自我调节学习中的最新研究进展和发展方向,研究以应用框架和融合路径为切入点,系统地分析国外近十年间的18篇高质量实证研究论文.一方面,从学习分析如何应用的角度分析其在自我调节学习中的实证场景、利益相关者和应用技术,得到应用框架;另一方面,从自我调节学习模型出发归纳学习分析支持自我调节学习的切入点、方法、途径和目标,得到融合路径.研究发现,学习分析丰富了自我调节学习的应用场景,以可视化技术为主要工具,通过对学习行为和学习策略的关注,实现以学习分析反馈优化自我调节学习的目标.但纵观全局,当前学习分析的应用更多是为了从侧面衡量、展示自我调节学习,而未从内部支持自我调节学习,即两者的融合仍停留于表层,且对伦理层面关注不足.最后,本研究得到相关启示,以期对后续研究提供理论依据和发展方向.     

网络开放课程之学习分析模式探微

如何对网络开放课程中的海量学习数据进行采集、存储、分析与表示,并利用分析结果做出决策、优化学习、提高绩效,日益成为亟待解决的问题。NMC地平线报告中介绍的学习分析技术有助于这一问题的解决。根据我国开放课程的现状与学习分析法的特征,开放课程环境下学习分析的研究对象与服务对象具有一定的特殊性。学习分析模式包括采集、存储、分析、表示与应用五个层级;建模时需充分考虑数据与利益相关者的特殊性。未来,学习分析模式的应用在理论基础、数据标准、算法模型、隐私与安全性等方面面临着挑战。     

基于教育数据的学习分析工具的功能探究

设计能够支撑有效教学的学习分析工具,是学习分析研究过程中的一个重要环节,也是实现因学定教的技术保障。文章首先分析了国内外学习分析工具的研究现状,并针对已有学习分析工具存在的问题,进行了学习分析工具的功能需求调查与分析。随后,文章以一线教与学的需求为设计驱动,设计了面向学生端和教师端的学习分析工具的功能原型。最后,文章以现有的教育云服务平台为技术支撑,对学习分析工具的功能进行技术实现,以期为精准教学的开展提供工具支持。