Eliciting motivation knowledge from log files towards motivation diagnosis for adaptive systems

Mihaela Cocea; S. Weibelzahl

Eliciting motivation knowledge from log files towards motivation diagnosis for adaptive systems

Mihaela Cocea
, S. Weibelzahl

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

402 Downloads (Pure)

Abstract

Motivation is well-known for its importance in learning and its influence on cognitive processes. Adaptive systems would greatly benefit from having a user model of the learner’s motivation, especially if integrated with information about knowledge. In this paper a log file analysis for eliciting motivation knowledge is presented, as a first step towards a user model for motivation. Several data mining techniques are used in order to find the best method and the best indicators for disengagement prediction. Results show a very good level of prediction: around 87% correctly predicted instances of all three levels of engagement and 93% correctly predicted instances of disengagement. Data sets with reduced attribute sets show similar results, indicating that engagement level can be predicted from information like reading pages and taking tests, which are common to most e-Learning systems.

Original language	English
Title of host publication	User Modeling 2007: 11th International Conference, UM 2007, Corfu, Greece, June 25-29, 2007, Proceedings
Editors	C. Conati, K. McCoy, G. Paliouras
Publisher	Springer
Pages	197-206
Number of pages	10
Edition	4511
ISBN (Print)	9783540730774
Publication status	Published - 2007
Event	User Modeling - Duration: 1 Jan 2007 → …

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Number	4511

Conference

Conference	User Modeling
Period	1/01/07 → …

UN SDGs

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

SDG 4 Quality Education

Access to Document

UM2007.pdfAccepted author manuscript (Post-print), 87.1 KB

http://dx.doi.org/10.1007/978-3-540-73078-1_23

Disengagement detection in online learning environments
Haig, E. (PI) & Weibelzahl, S. (CoI)
2/01/06 → 30/09/07
Project: Research

Cite this

Cocea, M., & Weibelzahl, S. (2007). Eliciting motivation knowledge from log files towards motivation diagnosis for adaptive systems. In C. Conati, K. McCoy, & G. Paliouras (Eds.), User Modeling 2007: 11th International Conference, UM 2007, Corfu, Greece, June 25-29, 2007, Proceedings (4511 ed., pp. 197-206). (Lecture notes in computer science; No. 4511). Springer. http://dx.doi.org/10.1007/978-3-540-73078-1_23

@inbook{c301d68af2bd4877aafb66bcae9dd281,

title = "Eliciting motivation knowledge from log files towards motivation diagnosis for adaptive systems",

abstract = "Motivation is well-known for its importance in learning and its influence on cognitive processes. Adaptive systems would greatly benefit from having a user model of the learner{\textquoteright}s motivation, especially if integrated with information about knowledge. In this paper a log file analysis for eliciting motivation knowledge is presented, as a first step towards a user model for motivation. Several data mining techniques are used in order to find the best method and the best indicators for disengagement prediction. Results show a very good level of prediction: around 87\% correctly predicted instances of all three levels of engagement and 93\% correctly predicted instances of disengagement. Data sets with reduced attribute sets show similar results, indicating that engagement level can be predicted from information like reading pages and taking tests, which are common to most e-Learning systems.",

author = "Mihaela Cocea and S. Weibelzahl",

year = "2007",

language = "English",

isbn = "9783540730774",

series = "Lecture notes in computer science",

publisher = "Springer",

number = "4511",

pages = "197--206",

editor = "C. Conati and K. McCoy and G. Paliouras",

booktitle = "User Modeling 2007: 11th International Conference, UM 2007, Corfu, Greece, June 25-29, 2007, Proceedings",

address = "Netherlands",

edition = "4511",

note = "User Modeling ; Conference date: 01-01-2007",

}

Cocea, M & Weibelzahl, S 2007, Eliciting motivation knowledge from log files towards motivation diagnosis for adaptive systems. in C Conati, K McCoy & G Paliouras (eds), User Modeling 2007: 11th International Conference, UM 2007, Corfu, Greece, June 25-29, 2007, Proceedings. 4511 edn, Lecture notes in computer science, no. 4511, Springer, pp. 197-206, User Modeling, 1/01/07. <http://dx.doi.org/10.1007/978-3-540-73078-1_23>

Eliciting motivation knowledge from log files towards motivation diagnosis for adaptive systems. / Cocea, Mihaela; Weibelzahl, S.
User Modeling 2007: 11th International Conference, UM 2007, Corfu, Greece, June 25-29, 2007, Proceedings. ed. / C. Conati; K. McCoy; G. Paliouras. 4511. ed. Springer, 2007. p. 197-206 (Lecture notes in computer science; No. 4511).

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

TY - CHAP

T1 - Eliciting motivation knowledge from log files towards motivation diagnosis for adaptive systems

AU - Cocea, Mihaela

AU - Weibelzahl, S.

PY - 2007

Y1 - 2007

N2 - Motivation is well-known for its importance in learning and its influence on cognitive processes. Adaptive systems would greatly benefit from having a user model of the learner’s motivation, especially if integrated with information about knowledge. In this paper a log file analysis for eliciting motivation knowledge is presented, as a first step towards a user model for motivation. Several data mining techniques are used in order to find the best method and the best indicators for disengagement prediction. Results show a very good level of prediction: around 87% correctly predicted instances of all three levels of engagement and 93% correctly predicted instances of disengagement. Data sets with reduced attribute sets show similar results, indicating that engagement level can be predicted from information like reading pages and taking tests, which are common to most e-Learning systems.

AB - Motivation is well-known for its importance in learning and its influence on cognitive processes. Adaptive systems would greatly benefit from having a user model of the learner’s motivation, especially if integrated with information about knowledge. In this paper a log file analysis for eliciting motivation knowledge is presented, as a first step towards a user model for motivation. Several data mining techniques are used in order to find the best method and the best indicators for disengagement prediction. Results show a very good level of prediction: around 87% correctly predicted instances of all three levels of engagement and 93% correctly predicted instances of disengagement. Data sets with reduced attribute sets show similar results, indicating that engagement level can be predicted from information like reading pages and taking tests, which are common to most e-Learning systems.

M3 - Chapter (peer-reviewed)

SN - 9783540730774

T3 - Lecture notes in computer science

SP - 197

EP - 206

BT - User Modeling 2007: 11th International Conference, UM 2007, Corfu, Greece, June 25-29, 2007, Proceedings

A2 - Conati, C.

A2 - McCoy, K.

A2 - Paliouras, G.

PB - Springer

T2 - User Modeling

Y2 - 1 January 2007

ER -

Eliciting motivation knowledge from log files towards motivation diagnosis for adaptive systems

Abstract

Publication series

Conference

UN SDGs

Access to Document

Fingerprint

Projects

Disengagement detection in online learning environments

Cite this