Date of Award
2019
Type
Thesis
Major
Computer Science - Applied Computing Track
Degree Type
Master of Science
Department
TSYS School of Computer Science
First Advisor
Shamim Khan
Second Advisor
Rania Hodhod
Third Advisor
Hyrum D. Carroll
Abstract
The goal of automated essay evaluation is to assign grades to essays and provide feedback using computers. Automated evaluation is increasingly being used in classrooms and online exams. The aim of this project is to develop machine learning models for performing automated essay scoring and evaluate their performance. In this research, a publicly available essay data set was used to train and test the efficacy of the adopted techniques. Natural language processing techniques were used to extract features from essays in the dataset. Three different existing machine learning algorithms were used on the chosen dataset. The data was divided into two parts: training data and testing data. The inter-rater reliability and performance of these models were compared with each other and with human graders. Among the three machine learning models, the random forest performed the best in terms of agreement with human scorers as it achieved the lowest mean absolute error for the test dataset.
Recommended Citation
Ghanta, Harshanthi, "Automated Essay Evaluation Using Natural Language Processing and Machine Learning" (2019). Theses and Dissertations. 327.
https://csuepress.columbusstate.edu/theses_dissertations/327
