【作 者】：
吴林静， 涂凤娇， 马鑫倩， 高 喻， 刘清堂
【关 键 词 】：
在线协作会话； 人工智能； 概念模型； 可计算； 可理解
【栏 目】：
网络教育
【中文摘要】：
学习者的协作会话数据是深入了解其学习过程和认知状态的一类重要数据。但由于自然语言的灵活性和学习情境的复杂性，协作会话数据分析的自动化程度一直不高，难以大规模应用。文章从人工智能视域出发，构建了基于人工智能技术的在线协作会话分析概念模型，对在线协作会话分析的理论基础、基本特征、分析流程和常用方法进行了论述，并进一步详细分析了“基于信息论的知识贡献测量”和“基于语义的协作会话学习投入自动分析”两个在线协作会话分析典型案例。案例证明了该模型能够将人工智能技术的“可计算”与教育研究的“可理解”相结合，为人工智能技术与协作会话分析融合搭建了桥梁，对在线协作会话分析实践具有重要的指导和参考价值。
【英文摘要】：
Learners' collaborative conversation data is an important type of data for in-depth understanding their learning process and cognitive state. However, due to the flexibility of natural language and the complexity of learning contexts, the degree of automation of collaborative conversation data analysis is not high, and the data is difficult to be applied on a large scale. From the perspective of artificial intelligence, this paper constructs a conceptual model of online collaborative conversation analysis based on artificial intelligence technology, and discusses the theoretical basis, basic features, analysis process and common methods of online collaborative conversation analysis. Two typical cases of online collaborative conversation analysis, "Information Theory-based Knowledge Contribution Measurement" and "Semantic-based Automatic Analysis of Collaborative Conversation Learning Engagement", are further analyzed in detail. The cases demonstrate that this model can combine the "computability" of artificial intelligence technology with the "comprehensibility" of educational research, and build a bridge for the integration of artificial intelligence technology and collaborative conversation analysis, which is an important guide and reference for the practice of online collaborative conversation analysis.