Modeling Frustration Trajectories and Problem-Solving Behaviors in Adaptive Learning Environments for Introductory Computer Science

Abstract

Frustration, an inherent part of the classroom, is routinely associated with negative stigmas, however, if appropriately managed it can be a highly effective tool for excelling students. Often referred to as eustress, it is the principle that follows the premise of introducing students to a topic they are not familiar with, causing frustration as they learn the currently unfamiliar topic. In the experiment, a correlating pattern involving behavior can properly monitor frustration in a way that remains productive to the student. This process can be emulated using artificial intelligence in schools (AIED) to create adaptive algorithms that provide students with unfamiliar topics until the point that said student becomes sufficiently frustrated, at which point the AI would slow down the curriculum. Through discernment patterns in learners’ frustration levels and problem-solving strategies, AI can dynamically adjust the difficulty of tasks to accommodate each student’s personal needs, as well as the pacing of instruction, and the provision of support. In doing so, AIED could mitigate the adverse effects of extreme frustration and reaping the benefits of frustration that pushes students to a farther level than our current educational system can provide. With AIED creating the ideal structure of adaptive scaffolded learning, students’ needs can be individually fostered in a way that most preferably suits them. This ability to push students into learning curriculum at such an intricate level will allow students to further develop their independence when solving future problems as the high difficulty will authenticate the student's ability to grasp the concept extensively. The intricate interplay between AIED and frustration models is crucial for advancing the frontiers of human knowledge and pushing students to achieve their full potential.