Automated Content Grading Using Machine Learning (2004.04300v1)

Abstract: Grading of examination papers is a hectic, time-labor intensive task and is often subjected to inefficiency and bias in checking. This research project is a primitive experiment in the automation of grading of theoretical answers written in exams by students in technical courses which yet had continued to be human graded. In this paper, we show how the algorithmic approach in machine learning can be used to automatically examine and grade theoretical content in exam answer papers. Bag of words, their vectors & centroids, and a few semantic and lexical text features have been used overall. Machine learning models have been implemented on datasets manually built from exams given by graduating students enrolled in technical courses. These models have been compared to show the effectiveness of each model.