Improving early prediction of academic failure using sentiment analysis on self-evaluated comments

L. C. Yu, C. W. Lee, H. I. Pan, C. Y. Chou, P. Y. Chao, Z. H. Chen, S. F. Tseng, C. L. Chan, K. R. Lai

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

This study presents a model for the early identification of students who are likely to fail in an academic course. To enhance predictive accuracy, sentiment analysis is used to identify affective information from text-based self-evaluated comments written by students. Experimental results demonstrated that adding extracted sentiment information from student self-evaluations yields a significant improvement in early-stage prediction quality. The results also indicate the limited early-stage predictive value of structured data, such as homework completion, attendance, and exam grades, due to data sparseness at the beginning of the course. Thus, applying sentiment analysis to unstructured data (e.g., self-evaluation comments) can play an important role in improving the accuracy of early-stage predictions. The findings present educators with an opportunity to provide students with real-time feedback and support to help students become self-regulated learners. Using the exploring results for improvement in teaching and learning initiatives is important to maintain students' performances and the effectiveness of the learning process.

Original languageEnglish
Pages (from-to)358-365
Number of pages8
JournalJournal of Computer Assisted Learning
Volume34
Issue number4
DOIs
Publication statusPublished - 2018 Aug 1

Fingerprint

Students
student
homework
evaluation
learning process
Identification (control systems)
Teaching
educator
Feedback
present
learning
performance

Keywords

  • early prediction
  • learning analytics
  • sentiment analysis
  • unstructured data

ASJC Scopus subject areas

  • Education
  • Computer Science Applications

Cite this

Improving early prediction of academic failure using sentiment analysis on self-evaluated comments. / Yu, L. C.; Lee, C. W.; Pan, H. I.; Chou, C. Y.; Chao, P. Y.; Chen, Z. H.; Tseng, S. F.; Chan, C. L.; Lai, K. R.

In: Journal of Computer Assisted Learning, Vol. 34, No. 4, 01.08.2018, p. 358-365.

Research output: Contribution to journalArticle

Yu, L. C. ; Lee, C. W. ; Pan, H. I. ; Chou, C. Y. ; Chao, P. Y. ; Chen, Z. H. ; Tseng, S. F. ; Chan, C. L. ; Lai, K. R. / Improving early prediction of academic failure using sentiment analysis on self-evaluated comments. In: Journal of Computer Assisted Learning. 2018 ; Vol. 34, No. 4. pp. 358-365.
@article{2d368cdf0d674a0bb0e5b363624eb2a1,
title = "Improving early prediction of academic failure using sentiment analysis on self-evaluated comments",
abstract = "This study presents a model for the early identification of students who are likely to fail in an academic course. To enhance predictive accuracy, sentiment analysis is used to identify affective information from text-based self-evaluated comments written by students. Experimental results demonstrated that adding extracted sentiment information from student self-evaluations yields a significant improvement in early-stage prediction quality. The results also indicate the limited early-stage predictive value of structured data, such as homework completion, attendance, and exam grades, due to data sparseness at the beginning of the course. Thus, applying sentiment analysis to unstructured data (e.g., self-evaluation comments) can play an important role in improving the accuracy of early-stage predictions. The findings present educators with an opportunity to provide students with real-time feedback and support to help students become self-regulated learners. Using the exploring results for improvement in teaching and learning initiatives is important to maintain students' performances and the effectiveness of the learning process.",
keywords = "early prediction, learning analytics, sentiment analysis, unstructured data",
author = "Yu, {L. C.} and Lee, {C. W.} and Pan, {H. I.} and Chou, {C. Y.} and Chao, {P. Y.} and Chen, {Z. H.} and Tseng, {S. F.} and Chan, {C. L.} and Lai, {K. R.}",
year = "2018",
month = "8",
day = "1",
doi = "10.1111/jcal.12247",
language = "English",
volume = "34",
pages = "358--365",
journal = "Journal of Computer Assisted Learning",
issn = "0266-4909",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - Improving early prediction of academic failure using sentiment analysis on self-evaluated comments

AU - Yu, L. C.

AU - Lee, C. W.

AU - Pan, H. I.

AU - Chou, C. Y.

AU - Chao, P. Y.

AU - Chen, Z. H.

AU - Tseng, S. F.

AU - Chan, C. L.

AU - Lai, K. R.

PY - 2018/8/1

Y1 - 2018/8/1

N2 - This study presents a model for the early identification of students who are likely to fail in an academic course. To enhance predictive accuracy, sentiment analysis is used to identify affective information from text-based self-evaluated comments written by students. Experimental results demonstrated that adding extracted sentiment information from student self-evaluations yields a significant improvement in early-stage prediction quality. The results also indicate the limited early-stage predictive value of structured data, such as homework completion, attendance, and exam grades, due to data sparseness at the beginning of the course. Thus, applying sentiment analysis to unstructured data (e.g., self-evaluation comments) can play an important role in improving the accuracy of early-stage predictions. The findings present educators with an opportunity to provide students with real-time feedback and support to help students become self-regulated learners. Using the exploring results for improvement in teaching and learning initiatives is important to maintain students' performances and the effectiveness of the learning process.

AB - This study presents a model for the early identification of students who are likely to fail in an academic course. To enhance predictive accuracy, sentiment analysis is used to identify affective information from text-based self-evaluated comments written by students. Experimental results demonstrated that adding extracted sentiment information from student self-evaluations yields a significant improvement in early-stage prediction quality. The results also indicate the limited early-stage predictive value of structured data, such as homework completion, attendance, and exam grades, due to data sparseness at the beginning of the course. Thus, applying sentiment analysis to unstructured data (e.g., self-evaluation comments) can play an important role in improving the accuracy of early-stage predictions. The findings present educators with an opportunity to provide students with real-time feedback and support to help students become self-regulated learners. Using the exploring results for improvement in teaching and learning initiatives is important to maintain students' performances and the effectiveness of the learning process.

KW - early prediction

KW - learning analytics

KW - sentiment analysis

KW - unstructured data

UR - http://www.scopus.com/inward/record.url?scp=85050366990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050366990&partnerID=8YFLogxK

U2 - 10.1111/jcal.12247

DO - 10.1111/jcal.12247

M3 - Article

AN - SCOPUS:85050366990

VL - 34

SP - 358

EP - 365

JO - Journal of Computer Assisted Learning

JF - Journal of Computer Assisted Learning

SN - 0266-4909

IS - 4

ER -