Achieving Motivational and Cognitive Outcomes in Mathematics Using Enhanced Intelligent Tutoring Technology

许多教育研究都指出认知和动机过程在决定学习结果中的重要性。然而，我们还不了解这些过程如何随着时间的推移在个体学习者内部相互作用以产生特定的学习成果，以及不同形式的指导和辅导如何影响认知和动机的相互作用以促进学习。先进的学习技术，如智能辅导系统，通常集中在认知问题上，还没有解决动机问题。因此，在学习技术支持下的教育实践与人类学习的认知和动机方面的研究之间存在着重大差距。拟议项目的目标是调查在产生数学特定学习成果时学习者的能力、认知过程和支架策略之间的关系。它汇集了心理学，教育和信息技术领域的跨学科专家团队来从事这项工作。该项目将采用教育软件，旨在使我们能够解决和测量的激励和动机因素系统的方式。它将大大扩展智能教学系统和基于计算机的学习助手的工作，以真实的时间评估个人学习者的注意力和动机，推断他们的参与程度，并估计他们的领域知识。研究结果将在现实的学习条件下获得：洛杉矶的公立高中教室，学生人数反映了加州城市的种族，语言和经济多样性。该软件将根据专家导师使用的决策规则做出教学决策，这些专家导师考虑动机和认知目标以优化学习结果。教学策略也将以响应动画虚拟角色的形式实例化，以了解类人教学代理的存在是否会影响学习者的参与以及数学学习成果。课堂教师将能够通过创新的工具定制教学，以查看不断更新的评估和改进软件做出的教学决定。丰富的学习者数据集将在学生解决数学问题时自动收集，并将提供与特定学习成果相关的综合评估，包括解决单词问题和转移到嵌入真实世界STEM背景中的新颖，具有挑战性的问题。为了实现这一目标，研究人员将建立在先前NSF支持下开发的两个项目的结果基础上：一个经验验证的注意力跟踪系统的焦点，和一个智能辅导系统（ITS），专门用于提高学生的数学技能，这些学生在STEM研究领域的代表性历来不足。该项目的结果将通过提供个性化，在STEM相关的数学有效的基于网络的教学，将免费提供给学生在任何高中访问互联网。我们预计，影响将是最大的学生谁目前有动机困难的数学，包括妇女和代表性不足的群体。该项目的智力价值将是通过详细和真实的时间建模学习者个体的认知和参与的相互作用，并观察学习者知识的变化作为教学历史的函数，对学习过程的本质有更深的理解。

Much research in education now points to the importance of both cognitive andmotivational processes in determining learning outcomes. Yet we do not yet understandexactly how these processes interact within the individual learner over time to producespecific learning outcomes, and how different forms of instruction and tutoring caninfluence the interaction of cognition and motivation to facilitate learning. Advancedlearning technologies such as intelligent tutoring systems typically focus on cognitiveissues, and do not yet address motivational issues. Thus there is a major gap betweeneducational practice, as supported by learning technologies, and research in cognitive andmotivational aspects of human learning.The goal of the proposed project is to investigate the relations of learnerengagement, cognitive processes, and scaffolding strategies in producing specificlearning outcomes in mathematics. It brings together an interdisciplinary team ofspecialists in psychology, education, and information technology to pursue this work. Theproject will employ educational software designed to enable us to address and measurecognitive and motivational factors in systematic ways. It will significantly extendprevious work on intelligent tutoring systems and computer-based learning assistants toassess in real time the attention and motivation of individual learners, infer their level ofengagement, and estimate their domain knowledge. The research results will be obtainedin realistic learning conditions: public high school classrooms in Los Angeles, withstudent populations reflecting the ethnic, linguistic and economic diversity of urbanCalifornia. The software will make instructional decisions based on decision rules usedby expert human tutors who consider motivational and cognitive goals to optimizelearning outcomes. Instructional strategies will also be instantiated in the form of aresponsive animated virtual character, to learn if the presence of a human-likepedagogical agent influences the learner.s engagement as well as learning outcomes inmathematics. Classroom teachers will be able to customize the instruction throughinnovative tools to view continually updated assessments and refine pedagogicaldecisions made by the software. Rich learner data sets will be automatically collected asstudents work on mathematics problems, and will provide an integrated evaluation linkedto specific learning outcomes, including word problem solving and transfer to novel,challenging problems embedded in real-world STEM contexts. To accomplish this goal,the researchers will build on the results of two projects developed with prior NSF support: anempirically validated focus of attention tracking system, and an intelligent tutoringsystem (ITS) designed specifically to enhance math skills in students who have beentraditionally under-represented in STEM fields of study.The results of the project will have broad societal impact through providingindividualized, effective web-based instruction in STEM-related mathematics that will befreely accessible to students in any high school with access to the Internet. We anticipatethat the impact will be greatest among students who currently have motivationaldifficulties with mathematics, including women and underrepresented groups. Theintellectual merit of the project will be a deeper understanding of the very nature oflearning processes through the ability to model in detail and in real time the interaction ofcognition and engagement in the individual learner, and to observe changes in thelearner.s knowledge as a function of instructional history.