Fuzzy Intelligent System for Student Software Project Evaluation
Anna Ogorodova, Pakizar Shamoi, Aron Karatayev
TL;DR
The paper tackles the problem of subjective, resource-heavy evaluation of academic software projects in large classes. It introduces a fuzzy inference system that uses inputs for code quality, functionality, and inheritance usage to produce a quantifiable project success score, guided by criteria identified from surveys and expert input. A 36-rule fuzzy foundation is built on triangular and trapezoidal membership functions with centroid defuzzification, and validated through a simulation example (63.27% project success) and comparison with instructor assessments. The approach promises standardized, faster feedback and a practical evaluation workflow, with a prototype UI; limitations include dependence on expert-defined partitions and challenges in adapting to curriculum changes, suggesting future work on data-driven criterion definitions and expanding to teamwork-based criteria.
Abstract
Developing software projects allows students to put knowledge into practice and gain teamwork skills. However, assessing student performance in project-oriented courses poses significant challenges, particularly as the size of classes increases. The current paper introduces a fuzzy intelligent system designed to evaluate academic software projects using object-oriented programming and design course as an example. To establish evaluation criteria, we first conducted a survey of student project teams (n=31) and faculty (n=3) to identify key parameters and their applicable ranges. The selected criteria - clean code, use of inheritance, and functionality - were selected as essential for assessing the quality of academic software projects. These criteria were then represented as fuzzy variables with corresponding fuzzy sets. Collaborating with three experts, including one professor and two course instructors, we defined a set of fuzzy rules for a fuzzy inference system. This system processes the input criteria to produce a quantifiable measure of project success. The system demonstrated promising results in automating the evaluation of projects. Our approach standardizes project evaluations and helps to reduce the subjective bias in manual grading.