EAGER: Leveraging Behavioral and Physiological Feedback in the Design of Affect-Sensitive Distance Learning

随着世界劳动力越来越多地追求以技术为中心的职业，我们看到更多的技术学习环境出现，例如在线课程。 在线学习有许多优点，使其吸引成人学习者，如成本低，时间和节奏的灵活性，以及位置的方便。然而，也有许多缺点可以归因于缺乏面对面的互动。在在线学习环境中，教师无法观察学生是否有动力，参与，迷失或沮丧。 该项目将研究使用可穿戴技术和其他类型的传感器来收集更多关于在线学习者的上下文的可行性。 该研究将开发技术，将这些互补的传感技术，以了解更多关于在线学生的环境和他们的主观经验，在他们参与在线课程。这将产生方法来衡量在线学习环境中的社会背景。该项目的第二个关键目标是利用可穿戴设备和其他传感技术的洞察力，设计新的在线学习环境-以及为在线学生提供的实时教学-以更好地满足学习者的需求。该项目的创新之处在于多模态感知，以及对学生认知和情感状态的建模。我们的主要目标是收集和识别可穿戴传感器数据和学习措施之间的相关性;探索建模和在线教学之间的实时交互;并为学习系统的改进提供信息。该研究小组将研究学生，教师和计算机科学在线课程管理员的需求。这将创建一个大型数据库;计算机基础设施;集成传感，分析和建模模式的方法。该项目将开发一个真实世界的试点，与在线学习者和教师。试点研究将确认基础设施的可行性和可接受性，以及捕捉无聊、沮丧、喜悦和认知负荷迹象的能力。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

As the world workforce increasingly pursues technology-focused careers, we see more technology learning environments emerge, such as online courses. There are many advantages to online learning that make it appealing to adult learners, such as low cost, flexibility in times and pacing, and convenience of location. However, there are also many disadvantages that can be attributed to the lack of face-to-face interaction. In online learning environments, instructors cannot observe if students are motivated, engaged, lost or frustrated. This project will investigate the feasibility of using wearable technologies and other types of sensing to gather more context about the online learners. The research will develop techniques for incorporating these complementary sensing technologies to learn more about the online student's environment and their subjective experiences during their participation in online courses. This will generate methods to measure social context in online learning environments. The second key aim of the project is to use insights from wearable devices and other sensing technologies, to design new online learning environments - and the live instruction being given to online students - to better meet learners' needs. The innovation in this project lies in multi-modal sensing, coupled with modeling of students' cognitive and affective states. Our primary objectives are to collect and identify correlations between wearable sensor data and learning measures; to explore real-time interaction between modeling and online teaching; and to inform improvement of learning systems. The research team will study the needs of students, teachers and administrators of online courses in computer science. This will create a large database; computer infrastructure; methods for integrating across sensing, analytic, and modeling modalities. The project will develop a real-world pilot, with online learners and instructors. Studies of the pilot will confirm the feasibility and acceptability of the infrastructure, and the ability to capture signs of boredom, frustration, delight, and cognitive load.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.