文章基本信息

标题：Intelligent intervention by conversational agent through chatlog analysis
本地全文：下载
作者：Mike Procter ; Fuhua Lin ; Bob Heller 等
期刊名称：Smart Learning Environments
电子版ISSN：2196-7091
出版年度：2018
卷号：5
期号：1
页码：1-15
DOI：10.1186/s40561-018-0079-5
出版社：Springer Verlag
摘要：E-learning systems based on a conversational agent provide the basis of an intuitive, responsive, engaging interface for the online learner. This paper proposes an approach to intelligent intervention and strategic pedagogical design for improving student engagement when chatting with a conversational agent. First, we used previous conversational logs to detect and classify interaction behaviors of learners. And then we designed a set of strategies for intelligent intervention to improve learners’ engagement when conversing with the conversational agents.We implemented a multiagent framework to apply the strategy-based intervention. The effectiveness of learner interaction behaviors and the impact of intelligent intervention by the conversational agent were evaluated through chatlog analysis. Although not all of the quantitative tests were sensitive enough to detect the effect of the interventions, the findings suggest that the detection of behaviours was accurate. The interventions were observed to have the desired effect on behaviours associated with conversational engagement.
关键词：Conversational agent; Online learning; Behavior analysis; Engagement intelligent intervention