On the prediction of students’ quiz score by recurrent neural network

Fumiya Okubo, Takayoshi Yamashita, Atsushi Shimada, Yuta Taniguchi, Shinichi Konomi

Research output: Contribution to journalConference article

Abstract

In this paper, we explore the factor for improving the performance of prediction of students’ quiz scores by using a Recurrent Neural Network. The proposed method is applied to the log data of 2693 students in 15 courses that were conducted with following the common syllabus by 10 teachers. The experimental results show that in the case where the same teacher is not included in both training and test data, the accuracy of prediction slightly lower. We also show that at the beginning of a course, it is better to construct a prediction model including various items of learning logs, however, in the latter half, it is better to update the model by using selected information only.

Original languageEnglish
JournalCEUR Workshop Proceedings
Volume2163
Publication statusPublished - Jan 1 2018
Event2nd Multimodal Learning Analytics Across (Physical and Digital) Spaces, CrossMMLA 2018 - Sydney, Australia
Duration: Mar 6 2018 → …

Fingerprint

Recurrent neural networks
Students

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

On the prediction of students’ quiz score by recurrent neural network. / Okubo, Fumiya; Yamashita, Takayoshi; Shimada, Atsushi; Taniguchi, Yuta; Konomi, Shinichi.

In: CEUR Workshop Proceedings, Vol. 2163, 01.01.2018.

Research output: Contribution to journalConference article

@article{29ab5d7ff3ec46f0ba9c3943b08ed3d7,
title = "On the prediction of students’ quiz score by recurrent neural network",
abstract = "In this paper, we explore the factor for improving the performance of prediction of students’ quiz scores by using a Recurrent Neural Network. The proposed method is applied to the log data of 2693 students in 15 courses that were conducted with following the common syllabus by 10 teachers. The experimental results show that in the case where the same teacher is not included in both training and test data, the accuracy of prediction slightly lower. We also show that at the beginning of a course, it is better to construct a prediction model including various items of learning logs, however, in the latter half, it is better to update the model by using selected information only.",
author = "Fumiya Okubo and Takayoshi Yamashita and Atsushi Shimada and Yuta Taniguchi and Shinichi Konomi",
year = "2018",
month = "1",
day = "1",
language = "English",
volume = "2163",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

TY - JOUR

T1 - On the prediction of students’ quiz score by recurrent neural network

AU - Okubo, Fumiya

AU - Yamashita, Takayoshi

AU - Shimada, Atsushi

AU - Taniguchi, Yuta

AU - Konomi, Shinichi

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In this paper, we explore the factor for improving the performance of prediction of students’ quiz scores by using a Recurrent Neural Network. The proposed method is applied to the log data of 2693 students in 15 courses that were conducted with following the common syllabus by 10 teachers. The experimental results show that in the case where the same teacher is not included in both training and test data, the accuracy of prediction slightly lower. We also show that at the beginning of a course, it is better to construct a prediction model including various items of learning logs, however, in the latter half, it is better to update the model by using selected information only.

AB - In this paper, we explore the factor for improving the performance of prediction of students’ quiz scores by using a Recurrent Neural Network. The proposed method is applied to the log data of 2693 students in 15 courses that were conducted with following the common syllabus by 10 teachers. The experimental results show that in the case where the same teacher is not included in both training and test data, the accuracy of prediction slightly lower. We also show that at the beginning of a course, it is better to construct a prediction model including various items of learning logs, however, in the latter half, it is better to update the model by using selected information only.

UR - http://www.scopus.com/inward/record.url?scp=85051971820&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051971820&partnerID=8YFLogxK

M3 - Conference article

VL - 2163

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -