首页 | 本学科首页   官方微博 | 高级检索  
     检索      


Intelligent educational systems: identifying and decoupling the conversational levels
Authors:Geoff Cumming  John Self
Institution:(1) Department of Psychology, La Trobe University, 3083 Bundoora, Australia;(2) Department of Computing, Lancaster University, Lancaster, UK
Abstract:Intelligent educational systems (IESs) have traditionally been thought of in terms of their functional subsystems. The three obligatory subsystems are those containing domain knowledge, a model of the learner's current state, and teaching knowledge. We argue that it is useful to reconceptualise IESs: we should think of them from the point of view of the multiple levels of conversational interaction that they support with a learner. We suggest that in many cases it is useful to identify a task level at which the learner is working, and a higher discussion level at which the learner and system converse about, and reflect on the primary task. If the two levels can be to some extent decoupled, meaning that each level has less than complete knowledge of the other level, IES development might be simplified. In some cases an IES might be built by the addition of a discussion level component to an existing computer tool, simulation, game or microworld. A critical requirement for a decoupled IES is a representation for communication between levels; study of human tutoring is needed to guide identification of suitable representations.
Keywords:
本文献已被 SpringerLink 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号