学习分析视角下在线认知水平的评价模型研究

Research on the Evaluation Model of Online Cognitive Level from the Perspective of Learning Analytics

学习过程评价是在线教学的重要环节。然而,目前的学习过程评价存在三个困难:一是哪些指标能够反映在线学习的质量?二是如何及时了解在线学习过程中学习者的认知水平?三是对于学生数量较大的在线课程,是否能够实现对在线认知水平的自动评价?为此,需要以学习分析的思路,探索在线学习行为与在线认知水平之间的关系,确认能够表征在线认知能力的形成性评价指标,并尝试构建在线认知水平评价的学习分析模型。研究的对象是基于Moodle平台的一门纯网络课程,主要采用了内容分析法、社会网络分析法等,对自变量和因变量数据进行编码和量化,分析对象包括551个样本的行为数据及2459条讨论帖,并采用相关分析和多重线性回归进行数据分析。通过研究发现:(1)个体行为、交互行为、社会网络属性等三个维度的13个学习行为指标与在线认知水平显著相关;(2)"同伴回复"、"阅读帖子"、"发布帖子"等三个行为变量被纳入到表征认知能力的回归模型中,适合作为在线学习过程性评价的评价指标;(3)研究初步构建了在线认知水平的评价模型。基于这些研究结果,分别对用户画像类学习分析工具和评价类学习分析工具的设计与应用进行了讨论,以期为教师开展在线学习的过程性评价提供理论依据,为学习分析工具的设计与应用提供理论参考。

The evaluation of learning process is an important part of online teaching. However, there are three kinds of diffi-culty in the evaluation of learning process： Firstly, what indicators can reflect the quality of online learning？ Secondly, how to timely understand the cognitive level of learners in the online learning processg Thirdly, whether online courses with a larger number of stu-dents can realize the automatic evaluation of online cognitive level？ The study employed the method of learning analytics to explore the relationship between online learning behavior and online cognitive level. I t confirmed the formative evaluation indicators that could be used to characterize online cognitive ability, and tried to construct the learning analysis model of online cognitive level evaluation. The research object was a pure network course based on Moodle platform. This research mainly adopted the methods of content analy-sis and social network analysis to code and analyze the independent variables data and the dependent variable data, including the behavioral data of 551 samples and 2459 discussion posts. In addition, this study used correlation analysis and multiple linear regres-sion to analyze the data. The results were as follows： Firstly, 13 learning behavior indicators from the three dimensions such as indi-vidual behavior, interaction behavior and social network attribute were significantly correlated with online cognitive level. Secondly, three behavioral variables, such as peer response, reading post and making a pos t, were included in the regression model of cogni-tive ability, which were suitable as the evaluation indicators of online learning process evaluation. Thirdly, a preliminary evaluation model of online cognitive level was constructed in this study. Finally, the author discussed the design and application of learning ana-lytics tool, including the user portrait class and evaluation class. We hope that the results of this study can provide a theoretical basis for online learning process evaluation, and also provide a theoretical reference for the design and application of learning analysis tools.