Intelligent tutoring systems have been widely studied and applied to a variety of subjects. Most systems are based on traditional computer interfaces involving windows, icons, mouse, and pointer. Research shows that transfer from training to testing is greater when testing and training environments are similar, suggesting benefits from creating and evaluating tutoring systems with interfaces that match real-world problem-solving environments. This project aims to create pen-based tutoring systems that scaffold students in the same way they would ordinarily solve problems with paper and pencil. This goal is consistent with recent research comparing student performance across different user interfaces, demonstrating that the interfaces matching familiar work practice enhanced student performance.
From a technology perspective, the project will produce basic algorithms and user interfaces for creating pen-based tutoring software. From an education perspective, the project will develop and evaluate innovative pedagogical principles for individualizing statics instruction in pen-based environments. Statics is a critical field required for engineering and science majors.
The project will create computational techniques and tutoring systems for both tablet and pentop computers, and will assess the strengths and limitations of the two platforms. Comparisons will also be made with paper-and-pencil and traditional computer interfaces. A tablet computer has an LCD display with an integrated digitizer; the user writes directly on the display using a stylus. A pentop is a pen with an integrated digitizer and embedded processor. A pentop uses paper preprinted with a grid that allows the system to locate the pen tip and digitize pen strokes.
The tutors build upon two prototype, pen-based tutoring systems recently developed by the research team. The first, Newton's Pen, is a statics tutor implemented on the LeapFrog FLY pentop computer. The second, Kirchoff's Pen, uses a tablet computer to help students apply Kirchhoff's current and voltage laws. Preliminary studies with Newton's Pen show it is an effective teaching tool. The prototypes uncovered several important research issues that will be ad-dressed by the proposal. The project will: (1) develop new techniques for interpreting hand-written input to enable more fluid interaction with pen-based devices, (2) develop improved, pedagogically-sound user interface design principles for pen-based tutoring systems, (3) expand the class of statics problems beyond those investigated with Newton's Pen, (4) assess the educational value (both learning and transfer) of the tutors, and (5) identify the relative strengths and weaknesses of tablet and pentop platforms for instruction.
This project created computational techniques to enable natural, pen-based tutoring systems to teach students how to solve statics problems. Statics is the study of bodies in equilibrium under the influence of a set of forces. Statics is a particularly important field because it is required for most engineering and science majors. Nearly all such majors require physics courses that include statics, and most engineering disciplines require specialized statics courses. From a technology perspective, the project produced the basic algorithms and user interface principles for creating pen-based tutoring software that scaffolds students in solving problems in the same way they would ordinarily solve them with paper and pencil. From an education perspective, the project developed innovative pedagogical principles for individualized instruction in statics. We developed and evaluated three tutoring systems employing different user interface and instructional designs. The first system is used on a tablet computer with a stylus. The interface relies extensively on character and shape recognition to interpret the student’s writing. This system uses hierarchical tutorial feedback to critique the student’s complete free body diagrams and equations. The second system, called Newton’s Tablet, can be used either on a tablet computer with a stylus, or a traditional computer with a mouse. This system employs gesture recognition and utilizes either a virtual or physical keyboard for text entry. The instructional model used by this system is designed to enhance problem-solving transfer. This system requires students to make all of the reasoning steps in the solution process explicit, including those steps that are typically not recorded in a solution. It also employs a novel graphical approach to constructing equations that enables the student to focus on statics concepts before considering geometric and mathematical issues. The system critiques the student’s work after every problem-solving step. This instructional design has a number of intended benefits. First, it helps students to identify which structural elements of the problem guide the solution process. This is important for problem-solving transfer. Second, this design enables the system to more accurately diagnose student errors and provide effective feedback. Our third system uses the same instructional design as Newton’s Tablet, but operates on a smartpen, a writing instrument with an integrated digitizer and an embedded processor. A smartpen is used in conjunction with paper preprinted with a specially designed grid. As one writes on this "digital" paper, the digitizer uses the grid to locate the pen tip on the page and digitize the pen stroke. The digitized strokes are then analyzed and interpreted by the embedded processor. Developing applications for a smartpen is challenging because of limited memory and processing power, and because of the lack of a video display. However, a smartpen enables the student to work in a familiar pen-on-paper environment. Evaluations of our systems demonstrated that Newton’s Tablet was the most effective. In user studies, only brief exposure to this system was sufficient for students to achieve large and statistically significant learning gains. The use of gestures and keyboard entry of text results in fluid interaction with the system, which enables the student to focus on learning the subject matter. Also, the instructional design provides effective tutorial feedback to the student and enhances problem-solving transfer. We will continue to use Newton’s Tablet for instruction in two large undergraduate Mechanical Engineering courses at the University of California, Riverside. UCR is the most ethnically diverse campus in the UC system. It is one of the most diverse major research institutions in the United States, and has been designated a Hispanic Serving Institution by the Department of Education. This region has lower family income and less economic opportunity than most urban areas of California. Newton’s Tablet has the potential to increase the success of our students, thereby creating increased opportunities for students from traditionally underrepresented groups to succeed in an engineering career. This project resulted in the development of user interface design principles for creating instructionally-effective pen-based tutoring systems. The techniques developed will have broad applicability to the creation of user interfaces for systems with pen and touch input. With the widespread adoption of tablet computers and smartphones, there is a growing need for research in the creation of effective interfaces for pen and touch interaction. As online education, particularly massive open online courses (MOOCs), becomes an increasingly important component of undergraduate education, the type of tutoring system we developed will play an increasingly important role in education. For example, Newton’s Tablet can be used to provide individualized instruction to students on a large scale.
