Abstract:
Writing has been increasingly regarded as an important indicator for assessing skills. It is an important indicator to assess the skills acquired by students during the course of study. As tests, exams, become more and more popular and the number of students admitted becomes larger, it is a huge task to score so many questions by lecturers. So far, many methods have been used to solve this problem. In this research, incremental method of Latent Semantic Analysis was used to score essays. First, an n-gram language model was used to construct a Weighted Finite State Automata to perform text pre-processing and heuristic search to perform automated word segmentation of essays. Experimental results show that this pre-processing procedure is effective. After text pre-processing, Incremental Latent Semantic Analysis (ILSA) was used to perform automated essay scoring. Experimental results indicate that ILSA has a significant advantage in terms of both running time and memory usage. Furthermore, experimental results also show this system developed is quite effective with a scoring performance of 86.70% in correlation to human ratters. This system was able to grade essay containing tables and equations.
