Group mirrors to support interaction regulation in collaborative problem solving

Two experimental studies test the effect of group mirrors upon quantitative and qualitative aspects of participation in collaborative problem solving. Mirroring tools consist of a graphical representation of the group’s actions which is dynamically updated and displayed to the collaborators. In addition, metacognitive tools display a standard for desirable behavior. Results show that a mirroring tool did not substantively affect the behavior of subjects while a metacognitive tool led to increased participation in dialogue, including more frequent and precise planning.     

Studying teacher selection of resources in an ultra-large scale interactive system: Does metadata guide the way?

Ultra-large-scale interactive systems on the Internet have begun to change how teachers prepare for instruction, particularly in regards to resource selection. Consequently, it is important to look at how teachers are currently selecting resources beyond content or keyword search. We conducted a two-part observational study of an existing popular system called TeachersPayTeachers hypothesizing that ‘evaluative metadata’ (i.e. comments, ratings, and popularity measures) would drive selection of resources. The first part examined patterns in tens of thousands of sales overall, and the second part focused on patterns of sales in one focal topic that could be expert coded. We find that there are significant gaps in available metadata, that some aspects of metadata are closely associated with sales, and that metadata are weak correlates of expert-determined quality. We conclude by making suggestions for additional research and suggesting how ultra-large scale-interactive systems such as TeachersPayTeachers could be used to improve teacher education.     

基于WEB的知识分布式合作学习系统的设计与实现

基于WEB的教学系统正在流行,但多数局限于学生孤独地浏览网上教材,缺乏依靠网络而形成的同学之间相互讨论和经验分享,因而无法吸引学生上网学习,使用效果并不理想。文章提出了基于WEB平台的“知识分布式合作学习”的概念,它通过网络建立合作工作环境（CSCW）,形成虚拟的合作学习群体,促使教师与学生、学生与学生经验共享、信息交、讨论问题。文章介绍了该系统的设计与实现。     

协作学习中基于协同过滤的学习资源推荐研究

符合学习者特征的学习资源对于提高协作学习效率具有重要的影响。但是传统的学习资源推荐,没有充分考虑学习者、学习资源的特征和高效的推荐算法。针对上述问题,提出了基于协同过滤的学习资源推荐算法,根据学习者学习特征、学习资源特征和学习者对学习资源历史评价信息,采用协同过滤推荐算法,实现学习资源推荐。首先,通过学习者特征和学习资源的评分,寻找相似学习者并计算学习资源预测评分,然后根据该评分值和学习资源与学习者匹配度推荐学习资源,从而为学习者推荐符合自己兴趣爱好最合适的学习资源。实验结果表明该算法在个性化学习资源推荐的准确性上优于传统算法。     

基于Web的多媒体协同教学系统的设计与实现

结合现代教育理论,以CSCL（Computer Supported Collaborative Learming)模型为基础,引入了WBCL（Web Based Collaborative Learming)的概念,并依据CSCW设计理论和技术标准,提出了一个符合WBCL模式的、有效的远程师生交互、协同的虚拟教学环境模型一“虚拟教室”。该系统模型为身处异地的师生提供了一个基于Web的交互式协同教学环境,并在“虚拟教室”模型的基础上实现了一个基于Web的多点语音支持的多媒体师生交流系统。     

Collaborative knowledge building with wikis: The impact of redundancy and polarity

Wikis as shared digital artifacts may enable users to participate in processes of knowledge building. To what extent and with which quality knowledge building can take place is assumed to depend on the interrelation between people’s prior knowledge and the information available in a wiki. In two experimental studies we examined the impact on learning and knowledge building of the redundancy (Study 1) and polarity (Study 2) between participants’ prior knowledge and information available in the wiki. Based on the co-evolution model of cognitive and social systems, external assimilation and accommodation were used as dependent variables to measure knowledge building. The results supported the hypotheses that a medium level of redundancy and a high level of polarity foster external accommodation processes. External assimilation was stimulated by low redundancy and a high level of polarity. Moreover, we found that individual learning was influenced by the degree of external assimilation.     

基于Linux课程群的协作学习模式构建与实施方案设计

分析了Linux课程群的设置与教学进度。针对计算机专业Linux教学的特点和课程之间整合的过程,进行协作学习模式的构建与实施方案设计。并通过课程教学中的实践调查来检测学生在此模式下的认知效果。     

Supporting collaborative design activity in a multi-user digital design ecology

Across a broad range of design professions, there has been extensive research on design practices and considerable progress in creating new computer-based systems that support design work. Our research is focused on educational/instructional design for students' learning. In this sub-field, progress has been more limited. In particular, neither research nor systems development have paid much attention to the fact that design is becoming a more collaborative endeavor. This paper reports the latest research outcomes from R&D in the Educational Design Studio (EDS), a facility developed iteratively over four years to support and understand collaborative, real-time, co-present design work. The EDS serves to (i) enhance our scientific understanding of design processes and design cognition and (ii) provide insights into how designers' work can be improved through appropriate technological support. In the study presented here, we introduced a complex, multi-user, digital design tool into the existing ecology of tools and resources available in the EDS. We analysed the activity of four pairs of ‘teacher-designers’ during a design task. We identified different behaviors - in reconfiguring the task, the working methods and toolset usage. Our data provide new insights about the affordances of different digital and analogue design surfaces used in the Studio.     

A validity and reliability study of the Online Cooperative Learning Attitude Scale (OCLAS)

Determination of students' attitudes towards online cooperative learning is an important issue, which has not been studied adequately. In the literature, there are few scales to measure the attitude towards online cooperative learning for which validity and reliability have been proven. The main purpose of this study is to develop an attitude scale in order to specify students' attitudes towards online cooperative learning. The sample group is composed of 599 students for the first application and 242 students for the second. In order to detect the validity of the scale, exploratory and confirmatory factor analyses, item factor total correlations, corrected correlations and item discriminations were conducted. In order to assess the reliability of the scale, the level of internal consistency and the stability levels were calculated. OCLAS is a five-point Likert-type scale and includes 17 items that can be gathered under 2 factors. The analyses provided evidence that the Online Cooperative Learning Attitude Scale (OCLAS) is a valid and reliable scale that can be used in order to determine students' attitudes towards cooperative learning in online environments.     

Collaborative activities enabled by GroupScribbles (GS): An exploratory study of learning effectiveness

This paper describes the findings of an exploratory cycle of a design-based research project and examines the learning effectiveness of collaborative activities that are supported by the GroupScribbles (GS) software technology in two Singapore primary science classrooms. The students had ten weeks of GS-based lessons in science, which were co-designed by teachers and researchers to teach the curriculum by tapping on collaborative work in small groups as well as in the whole class. The results show that the GS classes performed better than non-GS classes as measured by traditional assessments. With GS, students were found to have more opportunities to participate in class discussions, and were exposed to diversified ideas. Analysis of data collected in the classroom as well as data on students’ attitudes and perceptions indicate that GS facilitated students’ collaborative learning, and improved students’ epistemology and attitudes toward science learning.     

基于CSCW系统协同学习的远程教育新模式

随着计算机网络技术的迅速发展和计算机协同工作CSCW（Conputer Supported Collaborative Work)理论和技术研究的深入，计算机协同学习（Computer Supported Collborative Learning)的思想逐渐被引入计算机网络远程教育的应用中，它打破了“背靠背”网络教学模式引发的交流障碍，在充分继承和发扬网络教学优势的基础上，更加强调老师和学生之间，学生和学生之间各种教学信息的实时交互性和学习的协同性，从而将传统课堂教学与网络教学的优势充分地结合起来。主要介绍基于CSCW系统中协作学习的基本概念和远程教育的基本模式。     

基于自组织社区发现的协作学习算法

远程学习者通常很难判断哪些学习资源最适合他们的阅读需要,同时对教师来说,针对每个学习者重新组织不同的学习资源几乎是不可能的。基于此,提出一种新颖的学习偏好建模方法,通过将动态学习数据映射为“资源、评估”的方式实现对学习特征的综合评估;通过构建智能代理来监控学习者的动态学习行为;提出组隶属度奖励机制和组成员交换机制,实现对分布式环境下的相似学习者的社区自组织;同时,基于JADE智能代理平台开发了一个协作学习平台,使得具有相似学习偏好的学习者能够进行学习资源和经验的共享。实验证明,算法具有较高的匹配准确性和社区构建效率,并能够切实提高协作学习的有效性。     

基于协同推荐学习资源系统的设计和实现

随着网上学习者的不断增多和网络学习资源的不断丰富,学习者需要系统能够推荐他们感兴趣的资源。通过使用ASP.NET设计开发学习资源网站,研究了协同过滤推荐技术的算法,并实现了基于协同推荐学习资源系统的设计。     

基于图的半监督协同训练算法

在分类器训练过程中,无标记数据的引入容易产生噪音,从而降低分类精度。为此,提出一种基于图的置信度估计半监督协同训练算法。利用样本数据自身的结构信息,计算无标记样本所属类别概率。采用多分类器对无标记数据进行置信度估计,以提高无标记数据挑选标准,减少噪音数据的引入。在UCI数据集上的对比实验验证了该算法的有效性。     

基于学习者个性因素的多Agent协同学习系统

未解决当前的远程教育系统存在形式单一和被动教学等问题,该文提出了一个基于学习者个性因素的多Agent学习系统模型。该模型结合智能代理技术,通过分析学习者个性因素,给出了个体Agent能力描述语言,提出了新的个性化分组策略和学习任务分配策略,采用补偿机制鼓励agent合作,结合状态空间搜索理论使M AS系统具有更强的解题能力,并可满足学习者主动学习的要求,还能在一定程度上节约系统的通讯。     

一种协同过滤式零次学习方法

深度学习算法在很多有监督学习任务上达到了令人满意的结果,但其依赖于大量标注样本,并且使用特定类别训练的分类器,只能对这些类别进行分类.零次学习希望计算机像人类一样,能够结合历史经验与知识进行推理,无需使用大量新类别样本训练,便可达到识别新类别的效果.发现了零次学习任务存在"冷启动"以及矩阵稀疏两个特点,这些特点在推荐任...     

Web学习环境中混合协同机制的研究

针对当前基于Web的教学系统设计中协同机制的优势和不足,深入分析和讨论了当前计算机支持的协作学习技术的应用和发展,基于CSCW理论提出了教学系统设计中混合协同机制的应用方法和策略,并基于混合协同机制完成了一个远程教学应用系统的设计,充分说明了多策略协同在Web学习系统设计中的有效性和重要意义。     

基于多核学习的协同滤波算法

协同滤波是当前推荐系统中一种主流的个性化推荐算法,通过近似用户对商品的评价进行推荐。核函数是解决非线性模式问题的一种方法。协同滤波通常会选用不同的核函数来分析用户之间的影响关系。由于单核函数无法适应于复杂多变场景。因此,结合多个核函数成为一种解决方法。多核学习能够针对场景来组合各个核函数以获取更好的结果。本文提出了一种基于多核学习的协同滤波算法。该算法在现有核函数的基础上,优化各个核函数的权重以匹配数据的分布。在大众点评数据集和Foursquare数据集上的实验结果表明：基于多核学习的协同滤波算法比经验给定的相似函数的性能要高,具有更好的普适性。