Comment data mining to estimate student performance considering consecutive lessons

Shaymaa E. Sorour, Kazumasa Goda, Tsunenori Mine

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The purpose of this study is to examine different formats of comment data to predict student performance. Having students write comment data after every lesson can reflect students' learning attitudes, tendencies and learning activities involved with the lesson. In this research, Latent Dirichlet Allocation (LDA) and Probabilistic Latent Semantic Analysis (pLSA) are employed to predict student grades in each lesson. In order to obtain further improvement of prediction results, a majority vote method is applied to the predicted results obtained in consecutive lessons. The research findings show that our proposed method continuously tracked student learning situations and improved prediction performance of final student grades.

Original languageEnglish
Pages (from-to)73-86
Number of pages14
JournalEducational Technology and Society
Volume20
Issue number1
Publication statusPublished - Jan 1 2017

Fingerprint

Data mining
Students
performance
student
learning situation
learning
voter
Semantics
semantics

All Science Journal Classification (ASJC) codes

  • Education
  • Sociology and Political Science
  • Engineering(all)

Cite this

Comment data mining to estimate student performance considering consecutive lessons. / Sorour, Shaymaa E.; Goda, Kazumasa; Mine, Tsunenori.

In: Educational Technology and Society, Vol. 20, No. 1, 01.01.2017, p. 73-86.

Research output: Contribution to journalArticle

@article{8ceb60ee55304dc4aae85d18508f77bf,
title = "Comment data mining to estimate student performance considering consecutive lessons",
abstract = "The purpose of this study is to examine different formats of comment data to predict student performance. Having students write comment data after every lesson can reflect students' learning attitudes, tendencies and learning activities involved with the lesson. In this research, Latent Dirichlet Allocation (LDA) and Probabilistic Latent Semantic Analysis (pLSA) are employed to predict student grades in each lesson. In order to obtain further improvement of prediction results, a majority vote method is applied to the predicted results obtained in consecutive lessons. The research findings show that our proposed method continuously tracked student learning situations and improved prediction performance of final student grades.",
author = "Sorour, {Shaymaa E.} and Kazumasa Goda and Tsunenori Mine",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "20",
pages = "73--86",
journal = "Educational Technology and Society",
issn = "1436-4522",
publisher = "IEEE Computer Society",
number = "1",

}

TY - JOUR

T1 - Comment data mining to estimate student performance considering consecutive lessons

AU - Sorour, Shaymaa E.

AU - Goda, Kazumasa

AU - Mine, Tsunenori

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The purpose of this study is to examine different formats of comment data to predict student performance. Having students write comment data after every lesson can reflect students' learning attitudes, tendencies and learning activities involved with the lesson. In this research, Latent Dirichlet Allocation (LDA) and Probabilistic Latent Semantic Analysis (pLSA) are employed to predict student grades in each lesson. In order to obtain further improvement of prediction results, a majority vote method is applied to the predicted results obtained in consecutive lessons. The research findings show that our proposed method continuously tracked student learning situations and improved prediction performance of final student grades.

AB - The purpose of this study is to examine different formats of comment data to predict student performance. Having students write comment data after every lesson can reflect students' learning attitudes, tendencies and learning activities involved with the lesson. In this research, Latent Dirichlet Allocation (LDA) and Probabilistic Latent Semantic Analysis (pLSA) are employed to predict student grades in each lesson. In order to obtain further improvement of prediction results, a majority vote method is applied to the predicted results obtained in consecutive lessons. The research findings show that our proposed method continuously tracked student learning situations and improved prediction performance of final student grades.

UR - http://www.scopus.com/inward/record.url?scp=85010297145&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010297145&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85010297145

VL - 20

SP - 73

EP - 86

JO - Educational Technology and Society

JF - Educational Technology and Society

SN - 1436-4522

IS - 1

ER -