Learning analytics initiatives in Latin America: Implications for educational researchers,practitioners and decision makers

This study presents several Latin American research initiatives in the field of learning analytics (LA). The study’s purpose is to enhance awareness and understanding of LA among researchers, practitioners and decision makers, and to highlight the importance of supporting research on LA. We analyzed case studies of LA research conducted at four levels of the educational system (the national, institutional, classroom and student levels), which were implemented in four countries (Brazil, Ecuador, Mexico and Uruguay). Diversified cases were selected to demonstrate the use of LA in primary, secondary and higher education, and to allow the inclusion of different types of datasets. These cases also showed the development of legal frameworks for handling ethical issues, and they met the requirements for data privacy protection in Latin America. The study concludes with a discussion of the findings and their implications for further research and practice in the field of LA for teaching and learning.     

Current initiatives,barriers, and opportunities for networked learning in Latin America

Educational technology research and development - This paper explores and describes the current initiatives, barriers, and opportunities for formal, non-formal, and informal networked learning...     

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。     

试比较东亚模式和拉美模式之异同

东亚模式和拉美模式是第三世界现代化进程中的两种发展模式,两种模式有各自的内容和特点,但总的看,东亚模式的经验多,拉美模式的教训多。两种模式同为资本主义性质的外源型现代化模式,因而也具备了一些共同点,如都出现了政治集权化,都重视改善当局与市场的关系。     

学习分析:大学教学信息化研究与实践的新领域

随着大学教学信息化进程的不断深化与发展,如何测量、挖掘、分析与利用在学习平台中积累的大量数据,以更好地支持教学与学习,进而改善和提升教与学的质量与效能,已成为摆在大学教学信息化研究者与实践者面前的现实课题。学习分析的兴起则为解决这一难题,提供了一系列的方法、工具和手段。文章将基于国内外学者的已有研究,通过对学习分析的发展脉络的梳理,对学习分析的内涵、过程、工具和方法作较为深入的解读,并尝试从推动大学教学创新的视角,阐释学习分析对促进大学教学信息化深入发展的重要价值和深远影响。     

拉丁美洲高等教育大众化探析

拉丁美洲国家在二十世纪六七十年代基本实现了高等教育大众化 ,采取的主要政策与措施包括改革公立高等教育 ,发展多层次的私立高等教育 ,创建公私立学校趋同的新型办学模式等。拉美国家高等教育大众化的成果是明显的 ,但也带来了职业分层化和投资效益低下等问题 ,其过度发展高等教育 ,忽视基础教育的教训应引起我们的警觉     

Towards a Prediction Model of Learning Performance: Informed by Learning Behavior Big Data Analytics

Using log data of 823 university students collected in two settings: their online learning setting and daily life setting (using campus ID cards for consumption purposes and book-borrowing in the university library), this study created indicators for online learning behavior, early-rising behavior, book-borrowing behavior and learning performance prediction. Five machine learning models were employed to analyze learning performance prediction, with the additional use of Boosting and Bagging to improve the accuracy of the prediction model. The predictability of the proposed model was also compared with that of both the Artificial Neural Network model and the Deep Neural Network model. At the same time, a classification rule set was established by combining decision tree and rule model, and a learning behavior diagnosis model combining decision tree and deep neural network was constructed. Findings showed that multi-scenario behavior performance indicators had strong predictive capabilities while the Deep Neural Network model had the highest prediction accuracy (82%) but was most time-consuming. The model based on the rule set is highly accurate, readable and operable and may be conducive to making accurate teaching interventions and resource recommendations.     

Teacher salaries in Latin America: A review

In this paper we use data from household surveys of 12 Latin American countries to assess how teacher salaries compare to workers in other occupations. The results show great variability from one country to another, ranging from an apparent underpayment of teachers in Bolivia by 35% relative to the control group, and a respective overpayment of 65% in Colombia. However, when statistical controls are introduced for the differential education, hours worked and gender composition between teachers and the comparison group, much of the earnings differential between the two groups disappears. On the basis of this finding, we cannot support the position that teachers are either overpaid or underpaid.     

学习共同体研究热点知识图谱分析

为科学清晰地展现国内外学习共同体研究成果,以中国知网（CNKI）与科学引文数据库（WOS）为文献来源,运用 CiteSpace V 软件的关键词共现聚类分析、研究机构共现分析和关键词时区共现分析等方法绘制知识图谱。研究发现,国内外学习共同体研究前沿包括教师专业学习共同体、网络学习共同体以及实践共同体 3大主流方向。研究热点聚焦教师专业发展、项目教学、合作学习、情景学习、教学策略开发等理论。未来学习共同体将与深度学习、泛在学习、自组织等理论结合产生新的生长点,对教师专业发展和网络学习具有重要推动作用。     

学习分析技术:挖掘大数据时代下教育数据的价值

当前,大数据时代已经来临,教育领域同样积累了海量数据。教育领域已经部署了众多的学习管理系统,在这些软件系统中存储着海量的学习者信息及学习过程数据。如何利用这些数据,使这些数据转变为信息、知识,并为教学决策、学习优化服务,已成为教育工作者以及学习者们所关注的内容。学习分析技术有助于发挥学习过程数据的价值,使数据成为审慎决策、过程优化的重要依据。该文介绍了国内外学习分析技术研究现状,归纳出学习分析技术的关键技术及分析模式,并以实例从不同用户视角包括管理者、辅导教师、学习者展示了学习分析技术在网络学习过程分析中的应用过程。     

基于MOOCs的多元同心学习分析模型构建

随着MOOCs在国内外迅猛发展,其高退学率低通过率导致教学效果不尽人意的问题,逐渐成为研究者关注的焦点。学习分析为解决该难题提供了一系列的研究方法和技术支持。为此,以学习分析促进MOOCs的个性化教育为核心,从学习过程、学习环境、教育环境、数据挖掘、应用支持服务、受益者等多元化视角出发,构建基于MOOCs的多元同心学习分析模型。并在已有研究的基础上归纳出支持该学习分析模型的关键技术。最终,以学习者特征识别、学习者在线学习行为分析、学习者交互分析三类典型应用来演示多元同心学习分析模型在MOOCs中的具体应用．以期为学习分析在M00Cs中的具体实施提供指导。     

从人力资本理论看拉丁美洲经济主义教育模式

二战后，在人力资本理论的推动下，多数拉美国家重视教育在发展中的地位和作用，大力增加对教育的投入。20世纪80年代以后，由于债务危机和经济危机的影响，用于教育的开支被大幅度削弱。通过探讨拉丁美洲的外债对教育的影响，分析拉美教育政策中需要改革以有效地适应经济发展的某些方面。     

罗斯福的欧洲及拉美政策与美国称霸世界

1933-1945年是世界历史进程发生巨变的年代，也是美国从问鼎世界向称霸转变的关键时期。处在这样一个非常时期的美国，如果不重新制定新的内政外交方略，就无法应对国内、国际的严峻形势。罗斯福根据国情、世情对美国传统的欧洲及拉丁美洲的外交政策作了大胆的扬弃。对欧洲，美国时而合纵连横，时而天马行空、独来独往，实施灵活外交政策；对拉丁美洲，睦邻政策替代了以往的大棒加金元政策。二战期间，美国彻底摆脱了“孤立主义”的枷锁，成为“民主国家的伟大兵工厂”。罗斯福时期的欧洲及拉美政策使美国以最小的代价实现了其问鼎世界的宏伟目标，并为二战后美国称霸世界莫定了基础。     

拉丁美洲城乡关系研究述评与展望

通过对国内外拉丁美洲城乡关系的研究成果进行归纳和梳理,对拉美城乡关系的概念界定、总体特征和研究现状进行了描述与分析,并在此基础上总结了相关研究的难点,提出了未来研究的展望。     

美国项目研究模式的学习概论

项目学习法(Project—based Lerning)是一种项目研究模式的学习，在当今美国的中小学里正进行着广泛而生动的实战。它旨在培养学生批判性的思维技能、生成新知识的知能，以及给学生创造一个体验式的学习过程与机会。     

全景透视多模态学习分析的数据整合方法

多模态学习分析被认为是学习分析研究的新生长点,其中,多模态数据如何整合是推进学习分析研究的难点。利用系统文献综述及元分析方法,有助于为研究和实践领域提供全景式的关于多模态数据整合的方法与策略指导。通过对国内外363篇相关文献的系统分析发现:(1)多模态学习分析中的数据类型主要包含数字空间数据、物理空间数据、生理体征数据、心理测量数据和环境场景数据等5类。在技术支持的教与学环境中,高频、精细、微观的多模态学习数据变得可得、易得、准确。(2)多模态学习分析中的学习指标主要有行为、注意、认知、元认知、情感、协作、交互、投入、学习绩效和技能等。随着技术的发展和人们对学习过程的深刻洞察,学习指标也会变得更加精细化。(3)数据与指标之间展现出"一对一""一对多"和"多对一"三种对应关系。把握数据与指标之间的复杂关系是数据整合的前提,测量学习指标时既要考虑最适合的数据,也要考虑其他模态数据的补充。(4)多模态学习分析中的数据整合方式主要有"多对一""多对多"和"三角互证"三种,旨在提高测量的准确性、信息的全面性和整合的科学性。总之,多模态数据整合具有数据的多模态、指标的多维度和方法的多样性等三维特性。将多模态数据时间线对齐是实现数据整合的关键环节,综合考虑三维特性提高分析结果的准确性是多模态数据整合未来研究的方向。     

拉美地区双语教育的发展困境及归因

拉美双语教育在20世纪80年代完成制度化后仍处于教育体系边缘,发展始终步履维艰,不容乐观。一方面政府当局未充分调动各方资源驱动改革,另一方面土著民族缺少必要资源推进改革。困境的根源来自于拉美主流意识形态中单语和单文化主义及种族主义对双语教育的压制和束缚,其背后反映的是土著民族现实诉求与殖民主义历史遗留这一根本性冲突。     

Mapping the terrain: Teach For America,charter school reform,and corporate sponsorship

In this paper we illustrate the relationships between Teach For America (TFA) and federal charter school reform to interrogate how policy decisions are shaped by networks of individuals, organizations, and private corporations. We use policy network analysis to create a visual representation of TFA’s key role in developing and connecting personnel, political support, and financial backing for charter reform. Next we examine how the networks unfold at a local level by zooming in on a case study of New Orleans. By mapping out these connections, we hope to provide a foundation for further investigation of how this network affects policies.     

拉丁美洲医学教育的变化、趋势与挑战

泛美医学院校协会(PAFAMS)董事PA Pulido等人撰文[Medical Teacher,2006,28(1):24-29]分析了拉丁美洲医学教育的多种影响因素,认为该地区的医学院校无计划地高速增长,质量得不到有效保障,卫生人力分布不合理.他们认为开展医学院校认证是解决上述问题的一条途径,并介绍了该地区医学院校认证的进展情况和趋势.     

Networked Learning and Learning Analytics: A Study on the Employment of Facebook in a Virtual Training Program

The growing popularity of Social Networking Sites (SNS) that are embedded with networked infrastructures serves as an ideal platform for developing a networked learning environment connecting geographically dispersed learners. Unlike the traditional learning systems which provide only limited sources of data, the learners engaged in virtual networked social environments tend to produce huge volumes of digital footprints that cannot be analyzed using conventional analytical techniques. Two new branches of analytical sciences – Educational Data Mining (EDM) and Learning Analytics (LA) – are being employed for processing digital data derived from online educational platforms in order to obtain meaningful inferences and data-driven insights.

Hence, the present experimental study involving a small group of geographically dispersed learners intend to examine the engagement level and interaction patterns that occur within a feminist networked learning environment created in Facebook using popular EDM and learning analytical techniques such as K-means Clustering, Social network analysis and correlation mining. Upon analysis, it was found that the peer network influence played a vital role in activating passive learners, eventually leading to the development of a closely bound networked learning community over time.