Watch the video

Notes here.

• Limitations of Traditional Homework [00:06:53]: The video points out that most students don't revisit homework after deadlines, limiting its potential as a learning tool beyond assessment.
• Introduction to Adaptive Learning Feedback [00:07:41]: Adaptive learning aims to tailor interactions between the platform and the student based on their knowledge and interaction, increasing learning efficiency.
• Learning Trees as a Simple Adaptive Approach [00:12:17]: Adapt utilizes "learning trees" or "decision trees" as a less computationally intensive form of adaptive learning compared to AI-driven systems.
• Student Agency in Learning Trees [00:12:51]: Students have control over their path within a learning tree, choosing which branches to explore based on their perceived needs.
• Benefits of Student Agency and Metacognition [00:13:16]: This approach encourages student engagement and helps develop metacognitive skills (understanding what they know and don't know).
• Financial Return on Investment [00:14:39]: Learning trees are presented as a more cost-effective adaptive learning solution compared to complex AI algorithms. Learning Trees allow faculty to guide the student, helping them identify where to focus their learning.
• Structure of Learning Tree Assignments [00:17:33]: An assignment can contain multiple learning trees, each offering a more complex learning experience than a single question.
• How Learning Trees Work for Students [00:18:18]: If a student answers a root question incorrectly, they can access a learning tree with exposition (instructional content) and assessment nodes.
• Earning a "Do-Over" [00:25:13]: Students typically earn the ability to retry the original question by engaging with, and completing the nodes within the learning tree.
• Instructor Control Over Tree Requirements [00:25:30]: Instructors can set requirements for how many branches students need to complete to earn a do-over, influencing the level of engagement.
• Learning Trees as "Choose Your Own Adventure" [00:26:01]: The speaker likens learning trees to this type of story, emphasizing student-driven exploration.
• Potential for Pre- and Post-Assessment [00:28:47]: Learning trees can facilitate pre- and post-assessments within the same assignment to measure learning gains.
• Student View of Interacting with a Learning Tree [00:33:22]: The video shows a student's perspective of answering a question incorrectly and then navigating a learning tree with exposition and assessment nodes.
• Criteria for Success in a Learning Tree (Student Perspective) [00:34:59]: Students need to engage with the nodes (spend time on exposition, answer assessment questions correctly) to progress and earn a do-over.
• Aligning Root Questions with Branches for Feedback [00:40:49]: The idea of designing root questions to directly correspond to the skills addressed in the branches to provide more specific feedback is explored.
• Creating Learning Trees Using Existing Questions and Resources [00:50:01]: Building learning trees can be efficient by leveraging existing questions and educational materials within the platform.
• Browse Existing Learning Trees [00:51:19]: Faculty can browse and utilize publicly available learning trees created by other users. They can also import them directly into their course.
• The Process of Building a New Learning Tree [00:54:55]: The video briefly demonstrates the interface for creating a new learning tree and adding questions and nodes.