Search
On-Site Program Calendar
Browse By Day
Browse By Time
Browse By Person
Browse By Room
Browse By Unit
Browse By Session Type
Search Tips
Change Preferences / Time Zone
Sign In
X (Twitter)
The vision of knowledge-in-use has been widely adopted in national science standards and international assessment programs (e.g., Organization for Economic Cooperation and Development, [OECD], 2019). In science education, a knowledge-in-use LP describes students’ development of core ideas and practices over time so that knowledge becomes more sophisticated allowing learners to apply their knowledge in new and compelling situations. However, there are many challenges in developing knowledge-in-use LPs to effectively support student science learning over time. For example, these forms of assessment tasks take a large amount of time for teachers to grade students' constructed responses (Krajcik, 2021), which impedes teachers from providing timely feedback for all students. Most teachers only provide general feedback to all students in class, such as “good job.” Providing immediate feedback for each student is impossible. Even though students have received feedback from their teachers, they may still need teachers’ instructional support to achieve knowledge-in-use learning goals. Those challenges impede the efficiency and effectiveness of such LP-based learning systems to support student knowledge-in-use development.
With the rapid development of digital technologies, artificial intelligence (AI) can serve as a partner to provide potential solutions to further support LP-based learning systems. In science education, AI technologies, such as Machine Learning (ML), have been widely used to develop algorithmic models to automatically score students constructed responses on assessment tasks (e.g., Haudek et al., 2012; Kaldaras et al., 2022; Linn et al., 2014; Zhai et al., 2022). Researchers have developed immediate feedback systems based on students' automatic scores (e.g., Lee et al., 2021; Ryoo & Linn, 2016). Research teams have recently designed dashboards to provide assessment information for teachers and students (Matuk et al., 2016; Moharreri et al., 2014).
This presentation addresses the essential research agenda on how AI can be applied to support student learning across time, especially in an LP-based learning system: 1) positioning theoretical perspectives and a conceptual model for integrating AI into LP in learning systems; 2) discussing our current work on integrating AI into knowledge-in-use LPs with automatic scoring information, personalized feedback, and instructional support in learning systems; and 3) envisioning the future research work with recommendations for AI-empowered LP-based learning systems.