A hybrid scheme for Automated Essay Grading based on LVQ and NLP techniques

Abstract

This paper presents a hybrid approach to an Automated Essay Grading System (AEGS) that provides automated grading and evaluation of student essays. The proposed system has two complementary components: Writing Features Analysis tools, which rely on natural language processing (NLP) techniques and neural network grading engine, which rely on a set of pre-graded essays to judge the student answer and assign a grade. By this way, students essays could be evaluated with a feedback that would improve their writing skills. The proposed system is evaluated using datasets from computer and information sciences college students' essays in Mansoura University. These datasets was written as part of mid-term exams in introduction to information systems course and Systems analysis and design course. The obtained results shows an agreement with teachers' grades in between 70% and nearly 90% with teachers' grades. This indicates that the proposed might be useful as a tool for automatic assessment of students' essays, thus leading to a considerable reduction in essay grading costs.