The Effectiveness of Intelligent Virtual Humans in Facilitating Self-Regulated Learning in STEM with MetaTutor

智能虚拟人通过 MetaTutor 促进 STEM 自我调节学习的有效性

• 批准号: 1431552
• 负责人: Roger Azevedo
• 金额: $ 136.56万
• 依托单位: North Carolina State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2014
• 资助国家: 美国
• 起止时间: 2014-09-01 至 2018-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1431552&HistoricalAwards=false
• 关键词: Effectiveness; Intelligent; Virtual; Humans; Facilitating

The investigators will research how characteristics of intelligent virtual humans (IVHs) support the ability of students to reflect on and, therefore, improve their learning in undergraduate biology. To date, research has shown mixed effectiveness when human avatars are used in learning technologies. To remedy that, the researchers will first study how expert human tutors use verbal and facial cues in reacting to students' cognitive, affective, metacognitive, and motivational (CAMM) processes. Then, they will use these data to build an enhanced intelligent virtual human tutor (by altering software called "MetaTutor"). The project will advance the field's ability to build more effective intelligent tutors and advance understanding of self-regulated learning. The researchers propose to experimentally study the effectiveness of the enhanced IVHs on learners' self-regulatory processes and other learning outcomes. Data will be collected on both a natural face and a natural face that has been morphed and presented as a virtual human. The facial and verbal expressions are meant to provide learners with an additional information source they can use to monitor and regulate their ongoing self-regulatory processes, including making accurate emotional appraisals. In addition to the facial data, the researchers will collect self-report data, trace data using a variety of sensors, learning outcomes (e.g., pretest and posttest), and knowledge construction activities (e.g., summaries of content, notes, quizzes). Finally, the project will be disseminated in the form of journal publications, conference presentations, and an enhanced version of MetaTutor.

研究人员将研究智能虚拟人(IVHS)的特征如何支持学生反思的能力，从而提高他们在本科生物学方面的学习。到目前为止，研究表明，当人类化身用于学习技术时，效果好坏参半。为了纠正这一点，研究人员将首先研究专家人类导师如何使用语言和面部线索对学生的认知、情感、元认知和动机(CAMM)过程做出反应。然后，他们将使用这些数据来构建一个增强型智能虚拟人类导师(通过更改名为“MetaTutor”的软件)。该项目将提高该领域建立更有效的智能导师的能力，并增进对自我调节学习的理解。研究人员建议通过实验研究增强的IVHS对学习者自我调节过程和其他学习结果的有效性。将收集自然人脸和变形后的自然人脸的数据，并将其呈现为虚拟人。面部和语言表达是为了为学习者提供一个额外的信息来源，他们可以用来监控和调节他们正在进行的自我调节过程，包括做出准确的情绪评估。除了面部数据，研究人员还将收集自我报告数据、使用各种传感器跟踪数据、学习结果(例如，前测和后测)以及知识构建活动(例如，内容摘要、笔记、测验)。最后，将以期刊出版物、会议报告和MetaTutor增强版的形式传播该项目。