Finding key integer values in many features for learners' academic performance prediction

Yudai Tanabe, Koki Kagari, Yuki Kitanaka, Kazuhiro Takeuchi, Sachio Hirokawa

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

1 Citation (Scopus)

Abstract

In recent years, along with the proliferation of the learning management system (LMS), a large amount of data regarding the interaction between the system and the learners has been accumulated. Correspondingly, various data mining methods have been applied to these data. In order to employ a suitable computational model that is at the core of the data mining method and is not automatically acquired by the mining method itself, it is important to make or find various reasonable hypotheses for target variables. In this paper, we propose a method for analyzing closely the degree to which the explanatory variables represented in integer value contributes to predicting categorical objective variables, such as a learner's academic performance. Specifically, we describe that a decision tree combining support vector machines (SVM) achieves accuracy consistent with existing research, and it contributes further extraction of particular explanatory values from the integer features. Before making a model with SVM, our proposal method expands original features represented by integer value to corresponding binary features. With this expansion of original features, we can identify the key values that closely relate to a learner's academic performance from behavioral features gathered from LMS. Identifying such key values in specific features plays an important role in developing a hypothesis that explains the objective variables, using them as explanatory variables. We believe that closer analysis of these key explanatory values will find latent knowledge that can improve learners' academic abilities.

Original languageEnglish
Title of host publicationProceedings of the 9th International Conference on Education Technology and Computers, ICETC 2017
PublisherAssociation for Computing Machinery
Pages167-171
Number of pages5
ISBN (Electronic)9781450354356
DOIs
Publication statusPublished - Dec 20 2017
Event9th International Conference on Education Technology and Computers, ICETC 2017 - Barcelona, Spain
Duration: Dec 20 2017Dec 22 2017

Other

Other9th International Conference on Education Technology and Computers, ICETC 2017
CountrySpain
CityBarcelona
Period12/20/1712/22/17

Fingerprint

Support vector machines
Data mining
Decision trees

All Science Journal Classification (ASJC) codes

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

Cite this

Tanabe, Y., Kagari, K., Kitanaka, Y., Takeuchi, K., & Hirokawa, S. (2017). Finding key integer values in many features for learners' academic performance prediction. In Proceedings of the 9th International Conference on Education Technology and Computers, ICETC 2017 (pp. 167-171). Association for Computing Machinery. https://doi.org/10.1145/3175536.3175551

Finding key integer values in many features for learners' academic performance prediction. / Tanabe, Yudai; Kagari, Koki; Kitanaka, Yuki; Takeuchi, Kazuhiro; Hirokawa, Sachio.

Proceedings of the 9th International Conference on Education Technology and Computers, ICETC 2017. Association for Computing Machinery, 2017. p. 167-171.

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

Tanabe, Y, Kagari, K, Kitanaka, Y, Takeuchi, K & Hirokawa, S 2017, Finding key integer values in many features for learners' academic performance prediction. in Proceedings of the 9th International Conference on Education Technology and Computers, ICETC 2017. Association for Computing Machinery, pp. 167-171, 9th International Conference on Education Technology and Computers, ICETC 2017, Barcelona, Spain, 12/20/17. https://doi.org/10.1145/3175536.3175551
Tanabe Y, Kagari K, Kitanaka Y, Takeuchi K, Hirokawa S. Finding key integer values in many features for learners' academic performance prediction. In Proceedings of the 9th International Conference on Education Technology and Computers, ICETC 2017. Association for Computing Machinery. 2017. p. 167-171 https://doi.org/10.1145/3175536.3175551
Tanabe, Yudai ; Kagari, Koki ; Kitanaka, Yuki ; Takeuchi, Kazuhiro ; Hirokawa, Sachio. / Finding key integer values in many features for learners' academic performance prediction. Proceedings of the 9th International Conference on Education Technology and Computers, ICETC 2017. Association for Computing Machinery, 2017. pp. 167-171
@inproceedings{5c7be7b2c5c34a3c86d97afa7de4aabe,
title = "Finding key integer values in many features for learners' academic performance prediction",
abstract = "In recent years, along with the proliferation of the learning management system (LMS), a large amount of data regarding the interaction between the system and the learners has been accumulated. Correspondingly, various data mining methods have been applied to these data. In order to employ a suitable computational model that is at the core of the data mining method and is not automatically acquired by the mining method itself, it is important to make or find various reasonable hypotheses for target variables. In this paper, we propose a method for analyzing closely the degree to which the explanatory variables represented in integer value contributes to predicting categorical objective variables, such as a learner's academic performance. Specifically, we describe that a decision tree combining support vector machines (SVM) achieves accuracy consistent with existing research, and it contributes further extraction of particular explanatory values from the integer features. Before making a model with SVM, our proposal method expands original features represented by integer value to corresponding binary features. With this expansion of original features, we can identify the key values that closely relate to a learner's academic performance from behavioral features gathered from LMS. Identifying such key values in specific features plays an important role in developing a hypothesis that explains the objective variables, using them as explanatory variables. We believe that closer analysis of these key explanatory values will find latent knowledge that can improve learners' academic abilities.",
author = "Yudai Tanabe and Koki Kagari and Yuki Kitanaka and Kazuhiro Takeuchi and Sachio Hirokawa",
year = "2017",
month = "12",
day = "20",
doi = "10.1145/3175536.3175551",
language = "English",
pages = "167--171",
booktitle = "Proceedings of the 9th International Conference on Education Technology and Computers, ICETC 2017",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Finding key integer values in many features for learners' academic performance prediction

AU - Tanabe, Yudai

AU - Kagari, Koki

AU - Kitanaka, Yuki

AU - Takeuchi, Kazuhiro

AU - Hirokawa, Sachio

PY - 2017/12/20

Y1 - 2017/12/20

N2 - In recent years, along with the proliferation of the learning management system (LMS), a large amount of data regarding the interaction between the system and the learners has been accumulated. Correspondingly, various data mining methods have been applied to these data. In order to employ a suitable computational model that is at the core of the data mining method and is not automatically acquired by the mining method itself, it is important to make or find various reasonable hypotheses for target variables. In this paper, we propose a method for analyzing closely the degree to which the explanatory variables represented in integer value contributes to predicting categorical objective variables, such as a learner's academic performance. Specifically, we describe that a decision tree combining support vector machines (SVM) achieves accuracy consistent with existing research, and it contributes further extraction of particular explanatory values from the integer features. Before making a model with SVM, our proposal method expands original features represented by integer value to corresponding binary features. With this expansion of original features, we can identify the key values that closely relate to a learner's academic performance from behavioral features gathered from LMS. Identifying such key values in specific features plays an important role in developing a hypothesis that explains the objective variables, using them as explanatory variables. We believe that closer analysis of these key explanatory values will find latent knowledge that can improve learners' academic abilities.

AB - In recent years, along with the proliferation of the learning management system (LMS), a large amount of data regarding the interaction between the system and the learners has been accumulated. Correspondingly, various data mining methods have been applied to these data. In order to employ a suitable computational model that is at the core of the data mining method and is not automatically acquired by the mining method itself, it is important to make or find various reasonable hypotheses for target variables. In this paper, we propose a method for analyzing closely the degree to which the explanatory variables represented in integer value contributes to predicting categorical objective variables, such as a learner's academic performance. Specifically, we describe that a decision tree combining support vector machines (SVM) achieves accuracy consistent with existing research, and it contributes further extraction of particular explanatory values from the integer features. Before making a model with SVM, our proposal method expands original features represented by integer value to corresponding binary features. With this expansion of original features, we can identify the key values that closely relate to a learner's academic performance from behavioral features gathered from LMS. Identifying such key values in specific features plays an important role in developing a hypothesis that explains the objective variables, using them as explanatory variables. We believe that closer analysis of these key explanatory values will find latent knowledge that can improve learners' academic abilities.

UR - http://www.scopus.com/inward/record.url?scp=85044277527&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044277527&partnerID=8YFLogxK

U2 - 10.1145/3175536.3175551

DO - 10.1145/3175536.3175551

M3 - Conference contribution

AN - SCOPUS:85044277527

SP - 167

EP - 171

BT - Proceedings of the 9th International Conference on Education Technology and Computers, ICETC 2017

PB - Association for Computing Machinery

ER -