Correlation of grade prediction performance and validity of self-evaluation comments

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

To grasp a student's lesson attitude and learning situation and to give a feed back to each student are educational foundations. Goda et al. proposed the PCN method to estimate a learning situation from a comment freely written by students[6, 7]. The PCN method categorizes comments into three items of P (previous), C(current) and N(next). They pointed out a correlation between the student's final results and the validity of a descriptive content of item C, that is something related to understanding of the lesson and learning attitudes to the lesson. However, a problem left in their work is the badness of performance in prediction for upper grade students. This paper proposes two manners of utilization of PCN scores: the validity level determination for assessment, and for prediction performance of students' final grades. In order to validate the proposed manners of utilization, we conducted two experiments. First, we employed multiple regression analysis to calculate PCN scores that determine the validity level with respect to each viewpoint. Students who wrote comments with a high PCN score are considered as those who describe their learning attitude appropriately. We also applied a machine learning method SVM (support vector machine) to students' comments for predicting their final results in five grades of S, A, B, C and D. Experimental results illustrated that as comments of students get higher PCN scores, the prediction performance of the students' grades becomes higher.

Original languageEnglish
Title of host publicationSIGITE 2013 - Proceedings of the 2013 ACM SIGITE Annual Conference on Information Technology Education
Pages35-42
Number of pages8
DOIs
Publication statusPublished - Nov 14 2013
Event2013 13th ACM SIGITE Annual Conference on Information Technology Education, SIGITE 2013 - Orlando, FL, United States
Duration: Oct 10 2013Oct 12 2013

Other

Other2013 13th ACM SIGITE Annual Conference on Information Technology Education, SIGITE 2013
CountryUnited States
CityOrlando, FL
Period10/10/1310/12/13

Fingerprint

Students
evaluation
performance
student
learning situation
utilization
learning method
Regression analysis
learning
Support vector machines
Learning systems
regression analysis
Feedback
experiment
Experiments

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Education

Cite this

Goda, K., Hirokawa, S., & Mine, T. (2013). Correlation of grade prediction performance and validity of self-evaluation comments. In SIGITE 2013 - Proceedings of the 2013 ACM SIGITE Annual Conference on Information Technology Education (pp. 35-42) https://doi.org/10.1145/2512276.2512294

Correlation of grade prediction performance and validity of self-evaluation comments. / Goda, Kazumasa; Hirokawa, Sachio; Mine, Tsunenori.

SIGITE 2013 - Proceedings of the 2013 ACM SIGITE Annual Conference on Information Technology Education. 2013. p. 35-42.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Goda, K, Hirokawa, S & Mine, T 2013, Correlation of grade prediction performance and validity of self-evaluation comments. in SIGITE 2013 - Proceedings of the 2013 ACM SIGITE Annual Conference on Information Technology Education. pp. 35-42, 2013 13th ACM SIGITE Annual Conference on Information Technology Education, SIGITE 2013, Orlando, FL, United States, 10/10/13. https://doi.org/10.1145/2512276.2512294
Goda K, Hirokawa S, Mine T. Correlation of grade prediction performance and validity of self-evaluation comments. In SIGITE 2013 - Proceedings of the 2013 ACM SIGITE Annual Conference on Information Technology Education. 2013. p. 35-42 https://doi.org/10.1145/2512276.2512294
Goda, Kazumasa ; Hirokawa, Sachio ; Mine, Tsunenori. / Correlation of grade prediction performance and validity of self-evaluation comments. SIGITE 2013 - Proceedings of the 2013 ACM SIGITE Annual Conference on Information Technology Education. 2013. pp. 35-42
@inproceedings{2c8d626fcb1240bdbce58e6f4a4c8dcf,
title = "Correlation of grade prediction performance and validity of self-evaluation comments",
abstract = "To grasp a student's lesson attitude and learning situation and to give a feed back to each student are educational foundations. Goda et al. proposed the PCN method to estimate a learning situation from a comment freely written by students[6, 7]. The PCN method categorizes comments into three items of P (previous), C(current) and N(next). They pointed out a correlation between the student's final results and the validity of a descriptive content of item C, that is something related to understanding of the lesson and learning attitudes to the lesson. However, a problem left in their work is the badness of performance in prediction for upper grade students. This paper proposes two manners of utilization of PCN scores: the validity level determination for assessment, and for prediction performance of students' final grades. In order to validate the proposed manners of utilization, we conducted two experiments. First, we employed multiple regression analysis to calculate PCN scores that determine the validity level with respect to each viewpoint. Students who wrote comments with a high PCN score are considered as those who describe their learning attitude appropriately. We also applied a machine learning method SVM (support vector machine) to students' comments for predicting their final results in five grades of S, A, B, C and D. Experimental results illustrated that as comments of students get higher PCN scores, the prediction performance of the students' grades becomes higher.",
author = "Kazumasa Goda and Sachio Hirokawa and Tsunenori Mine",
year = "2013",
month = "11",
day = "14",
doi = "10.1145/2512276.2512294",
language = "English",
isbn = "9781450322393",
pages = "35--42",
booktitle = "SIGITE 2013 - Proceedings of the 2013 ACM SIGITE Annual Conference on Information Technology Education",

}

TY - GEN

T1 - Correlation of grade prediction performance and validity of self-evaluation comments

AU - Goda, Kazumasa

AU - Hirokawa, Sachio

AU - Mine, Tsunenori

PY - 2013/11/14

Y1 - 2013/11/14

N2 - To grasp a student's lesson attitude and learning situation and to give a feed back to each student are educational foundations. Goda et al. proposed the PCN method to estimate a learning situation from a comment freely written by students[6, 7]. The PCN method categorizes comments into three items of P (previous), C(current) and N(next). They pointed out a correlation between the student's final results and the validity of a descriptive content of item C, that is something related to understanding of the lesson and learning attitudes to the lesson. However, a problem left in their work is the badness of performance in prediction for upper grade students. This paper proposes two manners of utilization of PCN scores: the validity level determination for assessment, and for prediction performance of students' final grades. In order to validate the proposed manners of utilization, we conducted two experiments. First, we employed multiple regression analysis to calculate PCN scores that determine the validity level with respect to each viewpoint. Students who wrote comments with a high PCN score are considered as those who describe their learning attitude appropriately. We also applied a machine learning method SVM (support vector machine) to students' comments for predicting their final results in five grades of S, A, B, C and D. Experimental results illustrated that as comments of students get higher PCN scores, the prediction performance of the students' grades becomes higher.

AB - To grasp a student's lesson attitude and learning situation and to give a feed back to each student are educational foundations. Goda et al. proposed the PCN method to estimate a learning situation from a comment freely written by students[6, 7]. The PCN method categorizes comments into three items of P (previous), C(current) and N(next). They pointed out a correlation between the student's final results and the validity of a descriptive content of item C, that is something related to understanding of the lesson and learning attitudes to the lesson. However, a problem left in their work is the badness of performance in prediction for upper grade students. This paper proposes two manners of utilization of PCN scores: the validity level determination for assessment, and for prediction performance of students' final grades. In order to validate the proposed manners of utilization, we conducted two experiments. First, we employed multiple regression analysis to calculate PCN scores that determine the validity level with respect to each viewpoint. Students who wrote comments with a high PCN score are considered as those who describe their learning attitude appropriately. We also applied a machine learning method SVM (support vector machine) to students' comments for predicting their final results in five grades of S, A, B, C and D. Experimental results illustrated that as comments of students get higher PCN scores, the prediction performance of the students' grades becomes higher.

UR - http://www.scopus.com/inward/record.url?scp=84887315481&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887315481&partnerID=8YFLogxK

U2 - 10.1145/2512276.2512294

DO - 10.1145/2512276.2512294

M3 - Conference contribution

AN - SCOPUS:84887315481

SN - 9781450322393

SP - 35

EP - 42

BT - SIGITE 2013 - Proceedings of the 2013 ACM SIGITE Annual Conference on Information Technology Education

ER -