Noboru Matsuda

• Ph.D
• Professor (Associate) at North Carolina State University

Students learn by teaching others as tutors. Advancement in the theory of learning by teaching has given rise to many pedagogical agents. In this paper, we exploit a known cognitive theory that states if a tutee asks deep questions in a peer tutoring environment, a tutor benefits from it. Little is known about a computational model of such deep que...

Learning by teaching has been compared with learning by being tutored, aka cognitive tutoring, to learn algebra linear equations for 7th to 8th grade algebra. Two randomized-controlled trials with 46 and 141 6th through 8th grade students were conducted in 3 public schools in two different years. Students in the learning by teaching (LBT) condition...

Massive Open Online Courses (MOOCs) have expanded their influence in the education field, setting a new trend in technology and pedagogical areas. However, they have controversial issues such as high dropout rates and ineffective and unqualified course environments. Especially, it has been argued that MOOCs should provide an adaptive online learnin...

As AIED systems with agents and avatars are used by students in different world regions, we expect students to prefer ones that look like them according to the Similarity Attraction Hypothesis. We investigate this effect via a system with a customizable avatar deployed in 2 US regions and 2 Philippines regions. We find that US students do customize...

In this paper we study the effect of adaptive scaffolding to learning by teaching. We hypothesize that learning by teaching is facilitated if (1) students receive adaptive scaffolding on how to teach and how to prepare for teaching (the metacognitive hypothesis), (2) students receive adaptive scaffolding on how to solve problems (the cognitive hypo...

We hypothesize that when cognitive tutors are integrated into online courseware, the online courseware can provide a new type of adaptive instructions, such as impasse-driven adaptive remediation and need-based assessments. As a proof of concept, we have developed an adaptive online course on the Open Learning Initiative (OLI) platform by integrati...

We have developed a tablet application to support peer review learning for visual art education. The tablet-based front-end allows students to review others' work and provide comments in the form of written text and also comments drawn directly on the artwork (i.e., the direct comment). We hypothesize that (1) peer review would facilitate learning...

Personalized learning systems have shown significant learning gains when used in formal classroom teaching. Systems that use pedagogical agents for teaching have become popular, but typically their design does not account for multilingual classrooms. We investigated one such system in classrooms in the Philippines to see if and how students used co...

SimStudent is a machine-learning agent initially developed to help novice authors to create cognitive tutors without heavy programming. Integrated into an existing suite of software tools called Cognitive Tutor Authoring Tools (CTAT), SimStudent helps authors to create an expert model for a cognitive tutor by tutoring SimStudent on how to solve pro...

Building an intelligent agent that simulates human learning of math and science could potentially benefit both cognitive science, by contributing to the understanding of human learning, and artificial intelligence, by advancing the goal of creating humanlevel intelligence. However, constructing such a learning agent currently requires manual encodi...

We discuss methods for evaluating simulated learners associated with four different scientific and practical goals for simulated learners. These goals are to develop a precise theory of learning, to provide a formative test of alternative instructional approaches, to automate authoring of intelligent tutoring systems, and to use as a teachable agen...

This paper investigates the effect of meta-cognitive help in the context of learning by teaching. Students learned to solve algebraic equations by tutoring a teachable agent, called SimStudent, using an online learning environment, called APLUS. A version of APLUS was developed to provide meta-cognitive help on what problems students should teach,...

Authoring Intelligent Tutoring Systems is expensive and time consuming. To reduce costs, the Cognitive Tutor Authoring Tools and the Example-Tracing Tutor paradigm were developed to make the tutor authoring process more efficient. Under this paradigm, tutors are constructed by demonstrating behavior directly in a tutor interface, reducing the need...

In this paper we investigate how competition among tutees in the context of learning by teaching affects tutors’ engagement as well as tutor learning. We conducted this investigation by incorporating a competitive Game Show feature into an online learning environment where students learn to solve algebraic equations by teaching a synthetic peer, ca...

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, gamel...

We investigate cognitive factors that are predictive of learning gains when students learn to solve equations by teaching a synthetic peer, called SimStudent. Previous empirical studies showed that prior knowledge is strongly predictive of post-test scores. However, in a recent study in the Philippines that replicated our previous study in the USA,...

To study the impact of extrinsic motivational intervention, a competitive Game Show was integrated into an on-line learning environment where students learn algebra equation solving by teaching a synthetic peer learner, called SimStudent. In the Game Show, a pair of SimStudents competed with each other by solving challenging problems to achieve hig...

SimStudent, an intelligent-agent architecture that generates a cognitive model from worked-out examples, currently interacts with human subjects only in a limited capacity. In our application, SimStudent attempts to solve algebra equations, querying the user about the correctness of each step as it solves, and the user explains the step in natural...

Understanding how children perceive and interact with teachable agents (systems where children learn through teaching a synthetic character embedded in an intelligent tutoring system) can provide insight into the effects of so-cial interaction on learning with intelligent tutoring systems. We describe results from a think-aloud study where children...

This paper reports on a classroom practice that focuses on the effectiveness of peer review in drawing picture education for hard-of-hearing students. We developed a peer review application for art in special education (PRAISE). PRAISE consists of a basic evaluation function and a direct comment function that has been implemented in a tablet PC. We...

We have built Sim Student, a computational model of learning, and applied it as a peer learner that allows students to learn by teaching. Using Sim Student, 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 fa...

SimStudent is an educational software infrastructure which is designed to leverage the tutor effect in an on-line learning environment. Tutor effect is the phenomenon that students learn when they teach others. SimStudent allows students to learn by teaching a computer agent instead of their peers. SimStudent is a lively computer agent that induct...

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 hig...

Student modeling is one of the key factors that affects automated tutoring systems in making instructional decisions. A student model is a model to predict the probability of a student making errors on given problems. A good student model that matches with student behavior patterns often provides useful information on learning task difficulty and t...

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 stu...

The effect of tutor learning has been studied in various contexts, providing ample evidence to suggest that students learn when they teach others. Yet, the cognitive and social factors that facilitate or inhibit tutor learning are still not well understood. One factor that prohibited research progress in this area is that studying the tutor learnin...

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 SimStu-dent. SimStudent is a first pedagogical teachable agent that commits to genuine inductive learning and studied in authentic clas...

Learners that have better metacognition acquire knowledge faster than others who do not. If we had better models of such learning, we would be able to build a better metacognitive ed-ucational system. In this paper, we propose a computational model that uses a probabilistic context free grammar induc-tion algorithm yielding metacognitive learning b...

Is learning by solving problems better than learning from worked-out examples? Using a machine-learning program that learns cognitive skills from examples, we have conducted a study to compare three learning strategies: learning by solving problems with feedback and hints from a tutor, learning by generalizing worked-out examples exhaustively, and...

SimStudent is a machine-learning agent that learns cognitive skills by demonstration. It was originally developed as a building block of the Cognitive Tutor Authoring Tools (CTAT), so that the authors do not have to build a cognitive model by hand, but instead simply demonstrate solutions for SimStudent to automatically generate a cognitive model....

SimStudent is a machine-learning agent that learns cognitive skills by demonstration. SimStudent was originally built as a building block for Cognitive Tutor Authoring Tools to help an author build a cognitive model without heavy programming. In this paper, we evaluate a second use of SimStudent for student modeling for Intelligent Tutoring Systems...

The aim of this study is to build an intelligent authoring environment for Cognitive Tutors in which the author need not manually write a cognitive model. Writing a cognitive model usually requires days of programming and testing even for a well-trained cognitive scientist. To achieve our goal, we have built a machine learning agent - called a Simu...

A simulated student is a machine learning agent that learns a set of cognitive skills by observing solutions demon- strated by human experts. The learned cognitive skills are converted into a cognitive model for a Cognitive Tutor that is a computerized tutor that teaches human students the cognitive skills. In this paper, we analyze the characteris...

Two problem solving strategies, forward chaining and backward chaining, were compared to see how they affect students' learning of geometry theorem proving with construction. It has been claimed that backward chaining is inappropriate for novice students due to its complexity. On the other hand, forward chaining may not be appropriate either for th...

Two problem solving strategies, forward chaining and backward chaining, were compared to see how they affect students' learning of geometry theorem proving with con- struction. In order to determine which strategy accelerates learning the most, an intelligent tutoring system, the Advanced Geometry Tutor, was developed that can teach either strat- e...

We are building an intelligent authoring tool for Cognitive Tutors, a highly successful form of computer-based tutoring. The primary target users (the authors) are educators who are not familiar with cognitive task analysis and AI program-ming, which are essential tasks in building Cognitive Tutors. Instead of asking authors to write a cognitive mo...

Two problem solving strategies, forward chaining and backward chaining, were compared to see how they affect students' learning of geometry theorem proving with con- struction. In order to determine which strategy accelerates learning the most, an intelligent tutoring system, the Advanced Geometry Tutor, was developed that can teach either strategy...

Cognitive Tutors are known to be very effective, but with only a significant cost of cognitive modeling and programming to build a cognitive model representing domain principles and skills, which is written as a set of production rules. This study is building an intelligent authoring system that helps authors build a Cognitive Tutor. The basic idea...

This study investigates a procedure for proving arithmetic-free Euclidean geometry the- orems that involve construction. "Construction" means drawing additional geometric elements in the problem figure. Some geometry theorems require construction as a part of the proof. The basic idea of our construction procedure is to add only elements required f...

This study characterizes hinting strategies used by a human tutor to help students learn geometry theorem proving. Current tutoring systems for theorem proving provide hints that encourage (or force) the student to follow a fixed forward and/or backward chaining strategy. In order to find out if human tutors observed a similar constraint, a study w...

This study addresses a novel technique to build a graphical user interface (GUI) for an intelligent tutoring system (ITS) to help students to learn geometry theorem proving with construction - one of the most challenging and creative parts of elementary geometry. Students’ task is not only to prove theorems, but also to construct missing points and...

For many years, ITS researchers have strived to provide better instruction. They have various kinds of student models and expert models, as well as models of student-tutor interactions. However, little research have been conducted on in-structional planning, which attempts to make a sequence of instructions optimal for a student. Obviously, the bet...

A new model of problem solver for geometric theorems with construction of auxiliary lines is discussed. The problem solver infers based on schematic knowledge with diagrammatic information (diagrammatic schema, DS for short). The inference algorithm invokes forward and backward chaining. The diagrammatic schema as well as the inference algorithm wa...

The concept formation in humans is made through a process where the common items and rules in the observed events are extracted. The observed events may contain an event which is not consistent with the already formed concept. In such a case, the modification or restructuring of the concept takes place and an effort is made toward differentiation o...

This study is intended to investigate the role of the student model in ITS to develop an effective student model for adaptive instruction. We have provided the deeper level student model because just diagnose the problem solving knowledge applied by the student is not sufficient. The deeper level student model consists of diagnostic hypotheses whic...

This paper describes a framework to infer a student’s misconception from observed errors during problem solving processes. A human teacher can generate hypotheses about reasons for an error by observing a student’s problem solving process. He or she is also able to identify the student’s misconception during the verifying process of these hypothese...

Study on building powerful and robust problem solver for ITSs is described. The proposed problem solver is based on parallel computing technology to simulate some of the intelligent characteristics of human problem solving including the concurrency of thought, the case based reasoning, and the awareness of the key to problem solving. We propose the...

The aim of this study is to incorporate the technique of programming by demonstration (PBD) into an authoring tool for Cognitive Tutors. The pri- mary motivation of using PBD is to facilitate the authoring of Cognitive Tutors by educators, rather than AI programmers. That is, instead of asking authors to build a cognitive model representing a task...

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 peer-learning environment, we have investigated how tutee (i.e., SimStudent) learning affected tutor (i.e., human...