Prediction of Student Actions Using Weighted Markov Model

Xiaodi Huang; Jianming Yong; Jiuyong Li; Junbin Gao

doi:10.1109/ITME.2008.4743842

Prediction of Student Actions Using Weighted Markov Model

Xiaodi Huang, Jianming Yong, Jiuyong Li, Junbin Gao

Research output: Book chapter/Published conference paper › Conference paper › peer-review

5 Citations (Scopus)

36 Downloads (Pure)

Abstract

The Markov model has been applied to many prediction applications including the student models of intelligent tutoring systems. In this paper, we extend this well-known model to the weighted Markov model, and then apply it to student models in order to predict student behaviors. The prediction using our models is based not only on the frequency of collective behaviors of previous users, but also on the degrees of the relations between the predicted user and others. In doing so, a novel way is presented to quantify the similarities between previous students and the current active student. These similarity scores will be used as weights in the weighted Markov model.

Original language	English
Title of host publication	ITME 2008
Editors	Ramana Reddy
Place of Publication	USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	154-159
Number of pages	6
ISBN (Electronic)	9781424436163
DOIs	https://doi.org/10.1109/ITME.2008.4743842
Publication status	Published - 2008
Event	IEEE International Symposium on IT in Medicine and Education - Xiamen, China, China Duration: 12 Dec 2008 → 14 Dec 2008

Conference

Conference	IEEE International Symposium on IT in Medicine and Education
Country/Territory	China
Period	12/12/08 → 14/12/08

Access to Document

10.1109/ITME.2008.4743842

7838 postpubAccepted author manuscript, 173 KB

Cite this

@inproceedings{15d49a9eedd740dba2c68e6ad8b2341e,

title = "Prediction of Student Actions Using Weighted Markov Model",

abstract = "The Markov model has been applied to many prediction applications including the student models of intelligent tutoring systems. In this paper, we extend this well-known model to the weighted Markov model, and then apply it to student models in order to predict student behaviors. The prediction using our models is based not only on the frequency of collective behaviors of previous users, but also on the degrees of the relations between the predicted user and others. In doing so, a novel way is presented to quantify the similarities between previous students and the current active student. These similarity scores will be used as weights in the weighted Markov model.",

keywords = "Open access version available, Markov Model, Student Activity Prediction",

author = "Xiaodi Huang and Jianming Yong and Jiuyong Li and Junbin Gao",

note = "Imported on 03 May 2017 - DigiTool details were: publisher = USA: Institute of Electrical and Electronics Engineers (IEEE) Press, 2008. editor/s (773b) = Ramana Reddy; Event dates (773o) = 12-14 December, 2008; Parent title (773t) = IEEE International Symposium on IT in Medicine and Education.; IEEE International Symposium on IT in Medicine and Education ; Conference date: 12-12-2008 Through 14-12-2008",

year = "2008",

doi = "10.1109/ITME.2008.4743842",

language = "English",

pages = "154--159",

editor = "Ramana Reddy",

booktitle = "ITME 2008",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

}

TY - GEN

T1 - Prediction of Student Actions Using Weighted Markov Model

AU - Huang, Xiaodi

AU - Yong, Jianming

AU - Li, Jiuyong

AU - Gao, Junbin

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = USA: Institute of Electrical and Electronics Engineers (IEEE) Press, 2008. editor/s (773b) = Ramana Reddy; Event dates (773o) = 12-14 December, 2008; Parent title (773t) = IEEE International Symposium on IT in Medicine and Education.

PY - 2008

Y1 - 2008

N2 - The Markov model has been applied to many prediction applications including the student models of intelligent tutoring systems. In this paper, we extend this well-known model to the weighted Markov model, and then apply it to student models in order to predict student behaviors. The prediction using our models is based not only on the frequency of collective behaviors of previous users, but also on the degrees of the relations between the predicted user and others. In doing so, a novel way is presented to quantify the similarities between previous students and the current active student. These similarity scores will be used as weights in the weighted Markov model.

AB - The Markov model has been applied to many prediction applications including the student models of intelligent tutoring systems. In this paper, we extend this well-known model to the weighted Markov model, and then apply it to student models in order to predict student behaviors. The prediction using our models is based not only on the frequency of collective behaviors of previous users, but also on the degrees of the relations between the predicted user and others. In doing so, a novel way is presented to quantify the similarities between previous students and the current active student. These similarity scores will be used as weights in the weighted Markov model.

KW - Open access version available

KW - Markov Model

KW - Student Activity Prediction

U2 - 10.1109/ITME.2008.4743842

DO - 10.1109/ITME.2008.4743842

M3 - Conference paper

SP - 154

EP - 159

BT - ITME 2008

A2 - Reddy, Ramana

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

T2 - IEEE International Symposium on IT in Medicine and Education

Y2 - 12 December 2008 through 14 December 2008

ER -

Prediction of Student Actions Using Weighted Markov Model

Abstract

Conference

Access to Document

Fingerprint

Cite this