[论文解读] Design and Implementation of an Intelligent Educational Model Based on Personality and Learner's Emotion

Somayeh Fatahi, Nasser Ghasem-Aghaee|arXiv (Cornell University)|Apr 8, 2010

Educational Technology and Pedagogy参考文献 23被引用 14

一句话总结

本文提出了一种智能在线学习模型，该模型基于MBTI框架和OCC情绪模型，根据学习者的个性特征和实时情绪进行自适应调整。系统通过虚拟导师和虚拟同学代理动态调整学习风格与互动方式，在真实场景测试中显著提升了学习质量与学习者满意度。

ABSTRACT

The Personality and emotions are effective parameters in learning process. Thus, virtual learning environments should pay attention to these parameters. In this paper, a new e-learning model is designed and implemented according to these parameters. The Virtual learning environment that is presented here uses two agents: Virtual Tutor Agent (VTA), and Virtual Classmate Agent (VCA). During the learning process and depending on events happening in the environment, learner's emotions are changed. In this situation, learning style should be revised according to the personality traits as well as the learner's current emotions. VTA selects suitable learning style for the learners based on their personality traits. To improve the learning process, the system uses VCA in some of the learning steps. VCA is an intelligent agent and has its own personality. It is designed so that it can present an attractive and real learning environment in interaction with the learner. To recognize the learner's personality, this system uses MBTI test and to obtain emotion values uses OCC model. Finally, the results of system tested in real environments show that considering the human features in interaction with the learner increases learning quality and satisfies the learner.

研究动机与目标

• 开发一种能够根据个体学习者个性特征和情绪状态自适应调整的智能教育系统。
• 通过基于实时情绪与人格数据动态调整学习风格，提升学习质量。
• 通过具备独立人格的智能虚拟同学代理，模拟真实且富有吸引力的学习环境。
• 在真实教育环境中验证该模型的有效性。

提出的方法

• 系统采用迈尔斯-布里格斯类型指标（MBTI）对学习者的个性特征进行分类，并分配相应的学习风格。
• 采用OCC（Ortony, Collins, 和 Clore）模型检测并分类学习者在交互过程中的当前情绪状态。
• 虚拟导师代理（VTA）根据学习者的个性与情绪状态，选择并应用最合适的教学策略。
• 虚拟同学代理（VCA）被实现为具备独立人格的智能代理，以增强参与度并模拟社交学习动态。
• 系统持续监控学习者互动行为，并实时更新其情绪与人格相关档案。
• 该模型在真实教育环境中实现并进行了测试，以评估其可用性与有效性。

实验结果

研究问题

• RQ1 如何有效将人格特征与实时情绪整合到自适应在线学习系统中？
• RQ2 基于人格与情绪的动态学习风格调整对学习质量有何影响？
• RQ3 社交互动型虚拟同学代理的引入如何影响学习者参与度与满意度？
• RQ4 与非自适应模型相比，该系统在多大程度上提升了学习成效？

主要发现

• 系统成功识别并响应了学习者情绪的变化，借助OCC模型实现了实时自适应。
• 当系统根据学习者的情绪与人格档案进行调整时，学习者报告了更高的满意度。
• 虚拟同学代理的引入显著增强了学习环境的参与感与真实感。
• 与传统在线学习系统相比，该模型在真实场景测试中表现出更优的学习质量。
• 基于人格的学习风格自适应显著提升了学习者的表现与知识保持率。
• 系统对情绪状态的动态响应有效降低了学习者的挫败感，并提升了学习动机。