Flowchart-based Bayesian Intelligent Tutoring System for computer programming

There is a misconception of what programming is at the early stages of learning programming for Computer Science (CS) minors. More researches in this field have revealed that the lack of problem-solving skills, which is considered as one of the prominent shortcomings that novices deal with, is exacerbated by language syntax that the novices employ. A Flowchart-based Intelligent Tutoring System (FITS) is proposed in this research aimed at introducing the early stages of learning programming (CS1) to put the record straight. The students who have no prior knowledge of programming are the target audience of this research. In order to support novice programmers in beginning of programming, Bayesian network approach is applied mainly for decision making and to handle uncertainties in knowledge level of students. How to use Bayesian network to take full advantage of it as an inference engine for providing users with various guidance is described in this paper. Therefore, our proposed system provides users with dynamic guidance such as recommend learning goals, recommend options for flowchart development, and generate appropriate reading sequences. Additionally, our proposed system's architecture and its components are elaborated. Our future work is to evaluate the FITS by conducting an experimental study using novices.