A outliers analysis of learner's data based on user interface behaviors

Se Kim Yong; Bok Yoon Tae; Jin Cha Hyun; Mo Jung Young; Eric Wang; Hyong Lee Jee

doi:10.1109/ICALT.2007.25

A outliers analysis of learner's data based on user interface behaviors

Se Kim Yong
, Bok Yoon Tae
, Jin Cha Hyun
, Mo Jung Young
, Eric Wang
, Hyong Lee Jee

Department of Computer Science and Engineering

Sungkyunkwan University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

A learning diagnosis system collects data from a learner's learning process, and analyzes it to build a suitable model for the learner, which can then be incorporated into an intelligent tutoring system to provide customized tutoring services. However, if the collected data reflects inconsistent learner behaviors or unpredictable learning tendencies, then the reliability of the learner model is degraded. In this paper, the outliers in the learner's data are eliminated by a k-NN method. We apply this method to an experimental data set obtained using DOLLS-HI, a learner diagnosis system that uses housing interior learning contents to diagnose learning styles. The resulting diagnosis model shows improved reliability than before eliminating the outliers.

Original language	English
Title of host publication	Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007
Pages	935-936
Number of pages	2
DOIs	https://doi.org/10.1109/ICALT.2007.25
State	Published - 2007
Event	7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007 - Niigata, Japan Duration: 18 Jul 2007 → 20 Jul 2007

Publication series

Name	Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007

Conference

Conference	7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007
Country/Territory	Japan
City	Niigata
Period	18/07/07 → 20/07/07

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 4 Quality Education

Access to Document

10.1109/ICALT.2007.25

Cite this

Yong, S. K., Tae, B. Y., Hyun, J. C., Young, M. J., Wang, E., & Jee, H. L. (2007). A outliers analysis of learner's data based on user interface behaviors. In Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007 (pp. 935-936). Article 4281207 (Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007). https://doi.org/10.1109/ICALT.2007.25

@inproceedings{cd9d1d310bdc4b4995f0d62a18f6e796,

title = "A outliers analysis of learner's data based on user interface behaviors",

abstract = "A learning diagnosis system collects data from a learner's learning process, and analyzes it to build a suitable model for the learner, which can then be incorporated into an intelligent tutoring system to provide customized tutoring services. However, if the collected data reflects inconsistent learner behaviors or unpredictable learning tendencies, then the reliability of the learner model is degraded. In this paper, the outliers in the learner's data are eliminated by a k-NN method. We apply this method to an experimental data set obtained using DOLLS-HI, a learner diagnosis system that uses housing interior learning contents to diagnose learning styles. The resulting diagnosis model shows improved reliability than before eliminating the outliers.",

author = "Yong, \{Se Kim\} and Tae, \{Bok Yoon\} and Hyun, \{Jin Cha\} and Young, \{Mo Jung\} and Eric Wang and Jee, \{Hyong Lee\}",

year = "2007",

doi = "10.1109/ICALT.2007.25",

language = "English",

isbn = "076952916X",

series = "Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007",

pages = "935--936",

booktitle = "Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007",

note = "7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007 ; Conference date: 18-07-2007 Through 20-07-2007",

}

Yong, SK, Tae, BY, Hyun, JC, Young, MJ, Wang, E & Jee, HL 2007, A outliers analysis of learner's data based on user interface behaviors. in Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007., 4281207, Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007, pp. 935-936, 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007, Niigata, Japan, 18/07/07. https://doi.org/10.1109/ICALT.2007.25

A outliers analysis of learner's data based on user interface behaviors. / Yong, Se Kim; Tae, Bok Yoon; Hyun, Jin Cha et al.
Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007. 2007. p. 935-936 4281207 (Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A outliers analysis of learner's data based on user interface behaviors

AU - Yong, Se Kim

AU - Tae, Bok Yoon

AU - Hyun, Jin Cha

AU - Young, Mo Jung

AU - Wang, Eric

AU - Jee, Hyong Lee

PY - 2007

Y1 - 2007

N2 - A learning diagnosis system collects data from a learner's learning process, and analyzes it to build a suitable model for the learner, which can then be incorporated into an intelligent tutoring system to provide customized tutoring services. However, if the collected data reflects inconsistent learner behaviors or unpredictable learning tendencies, then the reliability of the learner model is degraded. In this paper, the outliers in the learner's data are eliminated by a k-NN method. We apply this method to an experimental data set obtained using DOLLS-HI, a learner diagnosis system that uses housing interior learning contents to diagnose learning styles. The resulting diagnosis model shows improved reliability than before eliminating the outliers.

AB - A learning diagnosis system collects data from a learner's learning process, and analyzes it to build a suitable model for the learner, which can then be incorporated into an intelligent tutoring system to provide customized tutoring services. However, if the collected data reflects inconsistent learner behaviors or unpredictable learning tendencies, then the reliability of the learner model is degraded. In this paper, the outliers in the learner's data are eliminated by a k-NN method. We apply this method to an experimental data set obtained using DOLLS-HI, a learner diagnosis system that uses housing interior learning contents to diagnose learning styles. The resulting diagnosis model shows improved reliability than before eliminating the outliers.

UR - https://www.scopus.com/pages/publications/47549119795

U2 - 10.1109/ICALT.2007.25

DO - 10.1109/ICALT.2007.25

M3 - Conference contribution

AN - SCOPUS:47549119795

SN - 076952916X

SN - 9780769529165

T3 - Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007

SP - 935

EP - 936

BT - Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007

T2 - 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007

Y2 - 18 July 2007 through 20 July 2007

ER -

Yong SK, Tae BY, Hyun JC, Young MJ, Wang E, Jee HL. A outliers analysis of learner's data based on user interface behaviors. In Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007. 2007. p. 935-936. 4281207. (Proceedings - The 7th IEEE International Conference on Advanced Learning Technologies, ICALT 2007). doi: 10.1109/ICALT.2007.25

A outliers analysis of learner's data based on user interface behaviors

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this