Detecting student at risk of failure: a case study of conceptualizing mining from internet access log files

Ruangsak Trakunphutthirak, Yen Cheung, Vincent C.S. Lee

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Predicting student academic performance can be done by using educational data mining. Machine learning techniques play an important role for predicting academic performance from the large-scale data like the internet access log files from a university. Current data sources are mainly manual collections of data or data from a single unit of study. This study highlights the use of a new data source by transforming a university log file to predict academic performance. The log file comprises student internet access activities and browsing categories. To detect overall student academic performance, we select the best prediction accuracy by enhancing two datasets and comparing different weights in the time and frequency domains. We found that the random forest technique provides the best way in these datasets to predict students at risk-of-failure. We also found that data from internet access activities reveals a better accuracy than data from browsing categories. The combination of two datasets reveals a better picture of students' internet utilization and thus indicates how students at risk-of-failure can be detected by their internet access activities and browsing behavior.

Original languageEnglish
Title of host publicationProceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018
Subtitle of host publication17–20 November 2018 Singapore
EditorsHanghang Tong, Zhenhui (Jessie) Li, Feida Zhu, Jeffrey Yu
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages365-371
Number of pages7
ISBN (Electronic)9781538692882
ISBN (Print)9781538692899
DOIs
Publication statusPublished - 2018
EventIEEE International Conference on Data Mining Workshops 2018 - Singapore, Singapore
Duration: 17 Nov 201820 Nov 2018
Conference number: 18th
http://icdm2018.org/

Conference

ConferenceIEEE International Conference on Data Mining Workshops 2018
Abbreviated titleICDMW 2018
CountrySingapore
CitySingapore
Period17/11/1820/11/18
Internet address

Keywords

  • educational data mining
  • internet access activities
  • log file
  • students at risk-of-failure

Cite this

Trakunphutthirak, R., Cheung, Y., & Lee, V. C. S. (2018). Detecting student at risk of failure: a case study of conceptualizing mining from internet access log files. In H. Tong, Z. J. Li, F. Zhu, & J. Yu (Eds.), Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018: 17–20 November 2018 Singapore (pp. 365-371). [8637431] Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICDMW.2018.00060
Trakunphutthirak, Ruangsak ; Cheung, Yen ; Lee, Vincent C.S. / Detecting student at risk of failure : a case study of conceptualizing mining from internet access log files. Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018: 17–20 November 2018 Singapore. editor / Hanghang Tong ; Zhenhui (Jessie) Li ; Feida Zhu ; Jeffrey Yu. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 365-371
@inproceedings{3b9a1711c1d2498dadfd25d05315135b,
title = "Detecting student at risk of failure: a case study of conceptualizing mining from internet access log files",
abstract = "Predicting student academic performance can be done by using educational data mining. Machine learning techniques play an important role for predicting academic performance from the large-scale data like the internet access log files from a university. Current data sources are mainly manual collections of data or data from a single unit of study. This study highlights the use of a new data source by transforming a university log file to predict academic performance. The log file comprises student internet access activities and browsing categories. To detect overall student academic performance, we select the best prediction accuracy by enhancing two datasets and comparing different weights in the time and frequency domains. We found that the random forest technique provides the best way in these datasets to predict students at risk-of-failure. We also found that data from internet access activities reveals a better accuracy than data from browsing categories. The combination of two datasets reveals a better picture of students' internet utilization and thus indicates how students at risk-of-failure can be detected by their internet access activities and browsing behavior.",
keywords = "educational data mining, internet access activities, log file, students at risk-of-failure",
author = "Ruangsak Trakunphutthirak and Yen Cheung and Lee, {Vincent C.S.}",
year = "2018",
doi = "10.1109/ICDMW.2018.00060",
language = "English",
isbn = "9781538692899",
pages = "365--371",
editor = "Hanghang Tong and Li, {Zhenhui (Jessie)} and Feida Zhu and Jeffrey Yu",
booktitle = "Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Trakunphutthirak, R, Cheung, Y & Lee, VCS 2018, Detecting student at risk of failure: a case study of conceptualizing mining from internet access log files. in H Tong, ZJ Li, F Zhu & J Yu (eds), Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018: 17–20 November 2018 Singapore., 8637431, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 365-371, IEEE International Conference on Data Mining Workshops 2018, Singapore, Singapore, 17/11/18. https://doi.org/10.1109/ICDMW.2018.00060

Detecting student at risk of failure : a case study of conceptualizing mining from internet access log files. / Trakunphutthirak, Ruangsak; Cheung, Yen; Lee, Vincent C.S.

Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018: 17–20 November 2018 Singapore. ed. / Hanghang Tong; Zhenhui (Jessie) Li; Feida Zhu; Jeffrey Yu. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 365-371 8637431.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Detecting student at risk of failure

T2 - a case study of conceptualizing mining from internet access log files

AU - Trakunphutthirak, Ruangsak

AU - Cheung, Yen

AU - Lee, Vincent C.S.

PY - 2018

Y1 - 2018

N2 - Predicting student academic performance can be done by using educational data mining. Machine learning techniques play an important role for predicting academic performance from the large-scale data like the internet access log files from a university. Current data sources are mainly manual collections of data or data from a single unit of study. This study highlights the use of a new data source by transforming a university log file to predict academic performance. The log file comprises student internet access activities and browsing categories. To detect overall student academic performance, we select the best prediction accuracy by enhancing two datasets and comparing different weights in the time and frequency domains. We found that the random forest technique provides the best way in these datasets to predict students at risk-of-failure. We also found that data from internet access activities reveals a better accuracy than data from browsing categories. The combination of two datasets reveals a better picture of students' internet utilization and thus indicates how students at risk-of-failure can be detected by their internet access activities and browsing behavior.

AB - Predicting student academic performance can be done by using educational data mining. Machine learning techniques play an important role for predicting academic performance from the large-scale data like the internet access log files from a university. Current data sources are mainly manual collections of data or data from a single unit of study. This study highlights the use of a new data source by transforming a university log file to predict academic performance. The log file comprises student internet access activities and browsing categories. To detect overall student academic performance, we select the best prediction accuracy by enhancing two datasets and comparing different weights in the time and frequency domains. We found that the random forest technique provides the best way in these datasets to predict students at risk-of-failure. We also found that data from internet access activities reveals a better accuracy than data from browsing categories. The combination of two datasets reveals a better picture of students' internet utilization and thus indicates how students at risk-of-failure can be detected by their internet access activities and browsing behavior.

KW - educational data mining

KW - internet access activities

KW - log file

KW - students at risk-of-failure

UR - http://www.scopus.com/inward/record.url?scp=85062822011&partnerID=8YFLogxK

U2 - 10.1109/ICDMW.2018.00060

DO - 10.1109/ICDMW.2018.00060

M3 - Conference Paper

SN - 9781538692899

SP - 365

EP - 371

BT - Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018

A2 - Tong, Hanghang

A2 - Li, Zhenhui (Jessie)

A2 - Zhu, Feida

A2 - Yu, Jeffrey

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Trakunphutthirak R, Cheung Y, Lee VCS. Detecting student at risk of failure: a case study of conceptualizing mining from internet access log files. In Tong H, Li ZJ, Zhu F, Yu J, editors, Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018: 17–20 November 2018 Singapore. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 365-371. 8637431 https://doi.org/10.1109/ICDMW.2018.00060