Automatic Code Homework Grading Based on Concept Extraction

E-learning is taking more roles in the current methods of education. The automatic grading and assessment play a major role in both e-learning and traditional education as a method to reduce educational expenses and relief instructors from some of the lengthy tasks such as grading. In this paper, automatic grading for software code assignments or homework is described. A tool is developed to automatically grade students\u27 code assignments. Concepts or code from Students\u27 answers are first parsed. Key abstractions and keywords are extracted from students\u27 assignments and compared with typical or expected answers. Weights are given to code keywords by the instructor based on their value and importance in the overall answer. Relating this grading with code plagiarism, similarities are also measured between students\u27 assignments and an Euclidean distance method is developed and calculated between each assignment with all other assignments. Results showed that automatic grading for code assignments can be automated due to the nature of expected answers where grader can set and expect a fixed number of possible keywords in each answer. Such formality may not exist for several other types of essay questions