This article describes an advanced learning technology used to investigate hypotheses about learning by teaching. The proposed technology is an instance of a teachable agent, called SimStudent, that learns skills (e.g., for solving linear equations) from examples and from feedback on performance. SimStudent has been integrated into an online, gamelike environment in which students act as “tutors” and can interactively teach SimStudent by providing it with examples and feedback. We conducted 3 classroom “in vivo” studies to better understand how and when students learn (or fail to learn) by teaching. One of the strengths of interactive technologies is their ability to collect detailed process data on the nature and timing of student activities. The primary purpose of this article is to provide an in-depth analysis across 3 studies to understand the underlying cognitive and social factors that contribute to tutor learning by making connections between outcome and process data. The results show several key cognitive and social factors that are correlated with tutor learning. The accuracy of students’ responses (i.e., feedback and hints), the quality of students’ explanations during tutoring, and the appropriateness of tutoring strategy (i.e., problem selection) all positively affected SimStudent’s learning, which further positively affected students’ learning. The results suggest that implementing adaptive help for students on how to tutor and solve problems is a crucial component for successful learning by teaching.

We have built SimStudent, a computational model of learning, and applied it as a peer learner that allows students to learn by teaching. Using SimStudent, we study the effect of tutor learning. In this paper, we discuss an empirical classroom study where we evaluated whether asking students to provide explanations for their tutoring activities facilitates tutor learning -the self-explanation effect for tutor learning. The results showed that students in the self-explanation condition displayed the same amount of learning gain as students in the non-self-explanation condition, but with a significantly smaller number of problems tutored (during the same time). The study also showed an apparent increase in effectiveness relative to a prior study, which is arguably due to improvement of the system based on the iterative system-engineering effort.

This paper describes an application of a machine-learning agent, SimStudent, as a teachable peer learner that allows a student to learn by teaching. SimStudent has been integrated into APLUS (Artificial Peer Learning environment Using SimStudent), an on-line game-like learning environment. The first classroom study was conducted in local public high schools to test the effectiveness of APLUS for learning linear algebra equations. In the study, learning by teaching (i.e., APLUS) was compared with learning by tutored-problem solving (i.e., Cognitive Tutor). The results show that the prior knowledge has a strong influence on tutor learning -for students with insufficient training on the target problems, learning by teaching may have limited benefits compared to learning by tutored problem solving. It was also found that students often use inappropriate problems to tutor SimStudent that did not effectively facilitate the tutor learning.

Background: Medical student well-being is a critical issue in medical education and is linked to burnout and resilience. Understanding the impact of the clinical learning environment may be crucial to developing effective curricular interventions. Objective: To determine factors affecting medical student well-being and perceived stress during clinical clerkships and describe any associations with the learning environment, resilience, and performance. Methods: This was a retrospective study of one cohort of medical students surveyed at the conclusion of third-year clinical clerkships using the Medical School Learning Environment Scale, Brief

Abstract.The purpose of the current study is to test whether we could create a system where students can learn by teaching a live machine-learning agent, called SimStudent. SimStudent is a computer agent that interactively learns cognitive skills through its own tutored-problem solving experience. We have developed a game-like learning environment where students learn algebra equations by tutoring SimStudent. While Simulated Students, Teachable Agents and Learning Companion systems have been created, our study is unique that it genuinely learns skills from student input. This paper describes the overview of the learning environment and some results from an evaluation study. The study showed that after tutoring SimStudent, the students improved their performance on equation solving. The number of correct answers on the error detection items was also significantly improved. On average students spent 70.0 minutes on tutoring SimStudent and used an average of 15 problems for tutoring.