Key attribute for predicting student academic performance

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

Abstract

Predicting student final score from student's attributes is an important issue of learning analytic. Not only to achieve high prediction performance but also to identifying the key attributes is an important research theme. This paper evaluated exhaustively the prediction performance based on all possible combinations of four types of attributes - behavioral features, demographic features, academic background, and parent participation. The behavioral features are given as numerical data. But, we represented them as pair of an attribute name and the value. This vectorization yields 417 dimensional data, while naively represented data has 68 dimension. By applyig support vector machine and feature selection, we obtained the optimal prediction performance, with respect to feature selection, with accuracy 0.8096 and F-measure 0.7726. We confirmed that the behavioral feature is so crucial that the accuracy reaches 0.7905 without other features except behavioral feature. The combination of behavior feature and demographic feature gained F-measure 0.7662.

Original languageEnglish
Title of host publicationProceedings of the 10th International Conference on Education Technology and Computers, ICETC 2018
PublisherAssociation for Computing Machinery
Pages308-313
Number of pages6
ISBN (Electronic)9781450365178
DOIs
Publication statusPublished - Oct 26 2018
Event10th International Conference on Education Technology and Computers, ICETC 2018 - Tokyo, Japan
Duration: Oct 26 2018Oct 28 2018

Publication series

NameACM International Conference Proceeding Series

Conference

Conference10th International Conference on Education Technology and Computers, ICETC 2018
CountryJapan
CityTokyo
Period10/26/1810/28/18

Fingerprint

Students
Feature extraction
Support vector machines

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Hirokawa, S. (2018). Key attribute for predicting student academic performance. In Proceedings of the 10th International Conference on Education Technology and Computers, ICETC 2018 (pp. 308-313). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3290511.3290576

Key attribute for predicting student academic performance. / Hirokawa, Sachio.

Proceedings of the 10th International Conference on Education Technology and Computers, ICETC 2018. Association for Computing Machinery, 2018. p. 308-313 (ACM International Conference Proceeding Series).

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

Hirokawa, S 2018, Key attribute for predicting student academic performance. in Proceedings of the 10th International Conference on Education Technology and Computers, ICETC 2018. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 308-313, 10th International Conference on Education Technology and Computers, ICETC 2018, Tokyo, Japan, 10/26/18. https://doi.org/10.1145/3290511.3290576
Hirokawa S. Key attribute for predicting student academic performance. In Proceedings of the 10th International Conference on Education Technology and Computers, ICETC 2018. Association for Computing Machinery. 2018. p. 308-313. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3290511.3290576
Hirokawa, Sachio. / Key attribute for predicting student academic performance. Proceedings of the 10th International Conference on Education Technology and Computers, ICETC 2018. Association for Computing Machinery, 2018. pp. 308-313 (ACM International Conference Proceeding Series).
@inproceedings{618dd01fbe6347228ec8e855e64c6b70,
title = "Key attribute for predicting student academic performance",
abstract = "Predicting student final score from student's attributes is an important issue of learning analytic. Not only to achieve high prediction performance but also to identifying the key attributes is an important research theme. This paper evaluated exhaustively the prediction performance based on all possible combinations of four types of attributes - behavioral features, demographic features, academic background, and parent participation. The behavioral features are given as numerical data. But, we represented them as pair of an attribute name and the value. This vectorization yields 417 dimensional data, while naively represented data has 68 dimension. By applyig support vector machine and feature selection, we obtained the optimal prediction performance, with respect to feature selection, with accuracy 0.8096 and F-measure 0.7726. We confirmed that the behavioral feature is so crucial that the accuracy reaches 0.7905 without other features except behavioral feature. The combination of behavior feature and demographic feature gained F-measure 0.7662.",
author = "Sachio Hirokawa",
year = "2018",
month = "10",
day = "26",
doi = "10.1145/3290511.3290576",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "308--313",
booktitle = "Proceedings of the 10th International Conference on Education Technology and Computers, ICETC 2018",

}

TY - GEN

T1 - Key attribute for predicting student academic performance

AU - Hirokawa, Sachio

PY - 2018/10/26

Y1 - 2018/10/26

N2 - Predicting student final score from student's attributes is an important issue of learning analytic. Not only to achieve high prediction performance but also to identifying the key attributes is an important research theme. This paper evaluated exhaustively the prediction performance based on all possible combinations of four types of attributes - behavioral features, demographic features, academic background, and parent participation. The behavioral features are given as numerical data. But, we represented them as pair of an attribute name and the value. This vectorization yields 417 dimensional data, while naively represented data has 68 dimension. By applyig support vector machine and feature selection, we obtained the optimal prediction performance, with respect to feature selection, with accuracy 0.8096 and F-measure 0.7726. We confirmed that the behavioral feature is so crucial that the accuracy reaches 0.7905 without other features except behavioral feature. The combination of behavior feature and demographic feature gained F-measure 0.7662.

AB - Predicting student final score from student's attributes is an important issue of learning analytic. Not only to achieve high prediction performance but also to identifying the key attributes is an important research theme. This paper evaluated exhaustively the prediction performance based on all possible combinations of four types of attributes - behavioral features, demographic features, academic background, and parent participation. The behavioral features are given as numerical data. But, we represented them as pair of an attribute name and the value. This vectorization yields 417 dimensional data, while naively represented data has 68 dimension. By applyig support vector machine and feature selection, we obtained the optimal prediction performance, with respect to feature selection, with accuracy 0.8096 and F-measure 0.7726. We confirmed that the behavioral feature is so crucial that the accuracy reaches 0.7905 without other features except behavioral feature. The combination of behavior feature and demographic feature gained F-measure 0.7662.

UR - http://www.scopus.com/inward/record.url?scp=85062767887&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062767887&partnerID=8YFLogxK

U2 - 10.1145/3290511.3290576

DO - 10.1145/3290511.3290576

M3 - Conference contribution

AN - SCOPUS:85062767887

T3 - ACM International Conference Proceeding Series

SP - 308

EP - 313

BT - Proceedings of the 10th International Conference on Education Technology and Computers, ICETC 2018

PB - Association for Computing Machinery

ER -