TY - GEN
T1 - Comments data mining for evaluating student's performance
AU - Sorour, Shaymaa E.
AU - Mine, Tsunenori
AU - Godaz, Kazumasa
AU - Hirokawax, Sachio
PY - 2014/9/29
Y1 - 2014/9/29
N2 - The present study proposes prediction approaches of student's grade based on their comments data. Students describe their learning attitudes, tendencies and behaviors by writing their comments freely after each lesson. The main difficulty of this research is to predict students' performance by separately using two class data in each lesson. Although students learn the same subject, there exist differences between the comments in the two classes. The proposed methods basically employ latent semantic analysis (LSA) and two types of machine learning technique: SVM (support vector machine) and ANN (artificial neural network) for predicting students' final results in four grades of S, A, B and C. Moreover, an overlap method was proposed to improve the accuracy prediction results, the method allows to accept two grades for one mark to get the correct relation between LSA results and students' grades. The proposed methods achieve 50.7% and 48.7% prediction accuracy of students' grades by SVM and ANN, respectively. To this end, the results of this study reported models of students' academic performance predictors that are valuable sources of understanding students' behavior and giving feedback to them so that we can improve their learning activities.
AB - The present study proposes prediction approaches of student's grade based on their comments data. Students describe their learning attitudes, tendencies and behaviors by writing their comments freely after each lesson. The main difficulty of this research is to predict students' performance by separately using two class data in each lesson. Although students learn the same subject, there exist differences between the comments in the two classes. The proposed methods basically employ latent semantic analysis (LSA) and two types of machine learning technique: SVM (support vector machine) and ANN (artificial neural network) for predicting students' final results in four grades of S, A, B and C. Moreover, an overlap method was proposed to improve the accuracy prediction results, the method allows to accept two grades for one mark to get the correct relation between LSA results and students' grades. The proposed methods achieve 50.7% and 48.7% prediction accuracy of students' grades by SVM and ANN, respectively. To this end, the results of this study reported models of students' academic performance predictors that are valuable sources of understanding students' behavior and giving feedback to them so that we can improve their learning activities.
UR - http://www.scopus.com/inward/record.url?scp=84918495647&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84918495647&partnerID=8YFLogxK
U2 - 10.1109/IIAI-AAI.2014.17
DO - 10.1109/IIAI-AAI.2014.17
M3 - Conference contribution
AN - SCOPUS:84918495647
T3 - Proceedings - 2014 IIAI 3rd International Conference on Advanced Applied Informatics, IIAI-AAI 2014
SP - 25
EP - 30
BT - Proceedings - 2014 IIAI 3rd International Conference on Advanced Applied Informatics, IIAI-AAI 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd IIAI International Conference on Advanced Applied Informatics, IIAI-AAI 2014
Y2 - 31 August 2014 through 4 September 2014
ER -