Evolution of an Intelligent Deductive Logic Tutor Using Data-Driven Elements
- PDF / 872,298 Bytes
- 32 Pages / 439.642 x 666.49 pts Page_size
- 94 Downloads / 184 Views
Evolution of an Intelligent Deductive Logic Tutor Using Data-Driven Elements Behrooz Mostafavi1 · Tiffany Barnes1
© International Artificial Intelligence in Education Society 2016
Abstract Deductive logic is essential to a complete understanding of computer science concepts, and is thus fundamental to computer science education. Intelligent tutoring systems with individualized instruction have been shown to increase learning gains. We seek to improve the way deductive logic is taught in computer science by developing an intelligent, data-driven logic tutor. We have augmented Deep Thought, an existing computer-based logic tutor, by adding data-driven methods, specifically; intelligent problem selection based on the student’s current proficiency, automatically generated on-demand hints, and determination of student problem solving strategies based on clustering previous students. As a result, student tutor completion (the amount of the tutor the students completed) steadily improved as data-driven methods were added to Deep Thought, allowing students to be exposed to more logic concepts. We also gained additional insights into the effects of different course work and teaching methods on tutor effectiveness. Keywords Deductive logic instruction · Intelligent tutoring systems · Data-driven methods
Behrooz Mostafavi
[email protected] Tiffany Barnes [email protected] 1
North Carolina State University, Raleigh NC, USA
Int J Artif Intell Educ
Introduction Deductive logic is an important fundamental topic in computer science education. Meyers (1990) outlined this necessity very clearly. He noted that almost every aspect of computer science required logic as a foundational basis in order to understand it. In 2003 a study conducted by Page (2003) confirmed the necessity of discrete math, including deductive logic, to computer science education. It is therefore in the interest of improving computer science education to improve how deductive logic is taught in the classroom. Individualized student instruction is one of the most effective educational strategies, and students who receive individualized instruction often perform significantly better on performance evaluations than students who receive classroom instruction (Ma et al. 2014; VanLehn 2011; Steenbergen-Hu and Cooper 2014). Computer learning environments that mimic aspects of human tutors have also been highly successful. Intelligent tutoring systems (ITS) have been shown to be highly effective in improving learning gains when used in combination with classroom instruction through scaffolding of domain concepts and contextualized, individual feedback (VanLehn et al. 2005). It is important for intelligent tutoring systems to present problems to students that are appropriate to the student’s current level of proficiency in the subject matter. Students are more likely to perform better in-tutor when given problems in their zone of proximal development through scaffolding of major concepts (Murray and Arroyo 2002; VanLehn 2006). Proper scaffolding increases l
Data Loading...
