Human-Computer Interaction & Psychology

This paper presents a generalized scheme for modeling learning in simple and more complex tasks, and shows how such a model can be applied to optimizing conditions of practice to maximize some desired performance. To enable this optimal allocation of lesson time, this paper describes how to quantify the preferences of students using utility functions that can be maximized. This conventional game theoretic approach is enabled by specifying a mathematical model that allows us to compute expected utility of various ...

Life itself, to me, is a journey. There are a lot of challenges and excitement along this long journey. Getting a PhD is one of such challenging but exciting tasks. There are many people that I would like to thank. Without their support, I would never have gone this far in this journey. First and foremost, I would like to thank my advisors Dr. Kenneth R. Koedinger and Dr. William W. Cohen for their wonderful advice as well as their support on my career. I have always felt that I am so fortunate to have them as my advisors. Their great views of the field as well as the inspiring discussions we had during our meetings have guided me to the right direction in research. As professors at Carnegie Mellon University, they are, by default, very busy. They have always been trying their best to squeeze any time they have to provide me with further advice in addition to our regular meetings. I remember there were times that they gave me comments on my paper or answered my urgent questions, even when it was late at night. My advisors do not only teach me how to do brilliant research, they also pay attention to my career. My advisors not only care about their student, but also can think from their student's point of view and provide great advice. I would also like to express my sincere gratitude to Dr. Tom Mitchell, Dr. Pat Langley and Dr. Raymond J. Mooney for serving on my committee. Thanks a lot for the thoughtful advice and thought-provoking questions. During my discussion with my committee members, I learned how to view my research from different perspectives. Their valuable expertise in various research areas has broadened my knowledge, and inspired ideas that I have not thought before. I am particularly grateful in the thought-provoking questions. Sometimes, the questions can be very challenging to address. I had to think through my work more thoroughly. This gave me an opportunity to rethink a lot of issues in my research, to help in getting a deeper understanding of my work, and to further improve my research. Furthermore, I thank my parents as well as my boyfriend for their endless support in my career. Because of my pursuit in research, I could not spend much time with them, especially my parents, who are in China. However, whenever I ask them whether I should continue my pursuit, they have always given me the same answer that I should choose whatever I want to do, and they will always support me. As a Chinese, sometimes, it is really hard to express my true feelings face-to-face. Therefore, I write it down here that thank you, and I love you all. Finally, my gratefulness goes to my friends, Yanan Chen, Bin Fan, Bin Fu,

SimStudent is a computational model of learning with its cognitive fidelity of learning being demonstrated especially in the way it makes human-like errors (Matsuda et al., 2009). Using SimStudent as a teachable agent in an interactive peerlearning environment, we have investigated how tutee (ie, SimStudent) learning affected tutor (ie, human student) learning. In this paper, we are particularly interested in how tutees' shallow learning affects tutor learning. We are also interested in how the errors that the tutee ...

Abstract. To study cognitive and social factors that facilitate the tutor-learning effect, we have developed an on-line game-like environment where students learn algebra equation solving by teaching a computer agent, called SimStudent. SimStudent is a first pedagogical teachable agent that commits to genuine inductive learning and studied in authentic classroom settings. Our Learning by Teaching (LBT) environment is also designed to be highly modular and domain independent. Furthermore, the tutoring interface used in the ...

Intelligent Tutoring Systems have been shown to be very effective in supporting learning in domains such as mathematics, physics, computer programming, etc. However, they are yet to achieve similar success in tutoring metacognition. While an increasing number of educational technology systems support productive metacognitive behavior within the scope of the system, few attempt to teach skills students need to become better future learners. To that end, we offer a set of empirically-based design principles for ...

The present research investigated whether immediate metacognitive feedback on students' help-seeking errors can help students acquire better help-seeking skills. The Help Tutor, an intelligent tutor agent for help seeking, was integrated into a commercial tutoring system for geometry, the Geometry Cognitive Tutor. Study 1, with 58 students, found that the real-time assessment of students' help-seeking behavior correlated with other independent measures of help seeking, and that the Help Tutor improved students' help-seeking behavior while ...

Abstract. Students often use available help facilities in an unproductive fashion. To improve students' help-seeking behavior we built the Help Tutor–a domain-independent agent that can be added as an adjunct to Cognitive Tutors. Rather than making help-seeking decisions for the students, the Help Tutor teaches better help-seeking skills by tracing students actions on a (meta) cognitive help-seeking model and giving students appropriate feedback. In a classroom evaluation the Help Tutor captured help-seeking errors that were associated ...

Interactive educational technologies, like intelligent tutoring systems, provide an excellent platform on which to perform research on metacognition. Such systems provide finegrained tracking and assessment of students' cognitive and metacognitive behaviors. They also facilitate the implementation of tightly controlled experiments within the context of real classrooms. This chapter covers recent research on the impact of different types of metacognitive support in intelligent tutoring systems on both the learning of domain ...

Assessment of students' self-regulated learning (SRL) requires a method for evaluating whether observed actions are appropriate acts of self-regulation in the specific learning context in which they occur. We review research that has resulted in an automated method for context-sensitive assessment of a specific SRL strategy, help seeking while working with an intelligent tutoring system. The method relies on a computer-executable model of the targeted SRL strategy. The method was validated by showing that it converges with other ...

Helping students' improve their metacognitive and self-regulation skills holds the potential to improve students' ability to learn independently. Yet, to date, there are relatively few success stories of helping students enhance their metacognitive skills using interactive learning environments. In this paper we describe the Self-Assessment Tutor, an intelligent tutoring system for improving the accuracy of the judgments students make regarding their own knowledge. A classroom evaluation of the Self-Assessment Tutor with 84 students found ...

Learning to think is about transfer. The scope of transfer is essentially a knowledge representation question. Experiences during learning can lead to alternative latent representations of the acquired knowledge, not all of which are equally useful. Productive learning facilitates a general representation that yields accurate behavior in a large variety of new situations, thus enabling transfer. This chapter explores two hypotheses. First, learning to think happens in pieces and these pieces, or knowledge components, are the ...

Intelligent tutoring systems are quite difficult and time intensive to develop. In this paper, we describe a method and set of software tools that ease the process of cognitive task analysis and tutor development by allowing the author to demonstrate, instead of programming, the behavior of an intelligent tutor. We focus on the subset of our tools that allow authors to create "Pseudo Tutors" that exhibit the behavior of intelligent tutors without requiring AI programming. Authors build user interfaces by direct manipulation and then use a Behavior Recorder tool to demonstrate alternative correct and incorrect actions. The resulting behavior graph is annotated with instructional messages and knowledge labels. We present some preliminary evidence of the effectiveness of this approach, both in terms of reduced development time and learning outcome. Pseudo Tutors have now been built for economics, analytic logic, mathematics, and language learning. Our data supports an estimate of about 25:1 ratio of development time to instruction time for Pseudo Tutors, which compares favorably to the 200:1 estimate for Intelligent Tutors, though we acknowledge and discuss limitations of such estimates.

Combining peer tutoring with an intelligent tutoring system (ITS) holds the promise of augmenting the current benefits of the ITS. We designed and implemented a peer tutoring approach as an addition to the Cognitive Tutor Algebra (CTA), an ITS for high school algebra. We then used 30 students to evaluate the potential of the peer tutoring addition to increase learning. Although students learned and interacted positively, peer tutors lacked the necessary expertise to adequately help their tutees.