Using HCI task modeling techniques to measure how deeply students model

Sylvie Girard, Lishan Zhang, Yoalli Hidalgo-Pontet, Kurt VanLehn, Winslow Burleson, Maria Elena Chavez-Echeagary, Javier Gonzalez-Sanchez

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

User modeling in AIED has been extended in the past decades to include affective and motivational aspects of learner's interaction in intelligent tutoring systems. An issue in such systems is researchers' ability to understand and detect students' cognitive and meta-cognitive processes while they learn. In order to study those factors, various detectors have been created that classify episodes in log data as gaming, high/low effort on task, robust learning, etc. When simulating students' learning processes in an ITS, a question remains as to how to create those detectors, and how reliable their simulation of the user's learning processes can be. In this article, we present our method for creating a detector of shallow modeling practices within a meta-tutor instructional system. The detector was defined using HCI (human-computer interaction) task modeling as well as a coding scheme defined by human coders from past users' screen recordings of software use. The detector produced classifications of student behavior that were highly similar to classifications produced by human coders with a kappa of .925.

Original languageEnglish (US)
Title of host publicationCEUR Workshop Proceedings
PublisherCEUR-WS
Pages31-40
Number of pages10
Volume1009
StatePublished - 2013
EventWorkshops at the 16th International Conference on Artificial Intelligence in Education, AIED 2013 - Memphis, United States
Duration: Jul 9 2013Jul 13 2013

Other

OtherWorkshops at the 16th International Conference on Artificial Intelligence in Education, AIED 2013
CountryUnited States
CityMemphis
Period7/9/137/13/13

Fingerprint

Human computer interaction
Students
Detectors
Intelligent systems

Keywords

  • Human-computer interaction
  • Intelligent tutoring system
  • Robust learning
  • Shallow learning
  • Task modeling

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Girard, S., Zhang, L., Hidalgo-Pontet, Y., VanLehn, K., Burleson, W., Chavez-Echeagary, M. E., & Gonzalez-Sanchez, J. (2013). Using HCI task modeling techniques to measure how deeply students model. In CEUR Workshop Proceedings (Vol. 1009, pp. 31-40). CEUR-WS.

Using HCI task modeling techniques to measure how deeply students model. / Girard, Sylvie; Zhang, Lishan; Hidalgo-Pontet, Yoalli; VanLehn, Kurt; Burleson, Winslow; Chavez-Echeagary, Maria Elena; Gonzalez-Sanchez, Javier.

CEUR Workshop Proceedings. Vol. 1009 CEUR-WS, 2013. p. 31-40.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Girard, S, Zhang, L, Hidalgo-Pontet, Y, VanLehn, K, Burleson, W, Chavez-Echeagary, ME & Gonzalez-Sanchez, J 2013, Using HCI task modeling techniques to measure how deeply students model. in CEUR Workshop Proceedings. vol. 1009, CEUR-WS, pp. 31-40, Workshops at the 16th International Conference on Artificial Intelligence in Education, AIED 2013, Memphis, United States, 7/9/13.
Girard S, Zhang L, Hidalgo-Pontet Y, VanLehn K, Burleson W, Chavez-Echeagary ME et al. Using HCI task modeling techniques to measure how deeply students model. In CEUR Workshop Proceedings. Vol. 1009. CEUR-WS. 2013. p. 31-40
Girard, Sylvie ; Zhang, Lishan ; Hidalgo-Pontet, Yoalli ; VanLehn, Kurt ; Burleson, Winslow ; Chavez-Echeagary, Maria Elena ; Gonzalez-Sanchez, Javier. / Using HCI task modeling techniques to measure how deeply students model. CEUR Workshop Proceedings. Vol. 1009 CEUR-WS, 2013. pp. 31-40
@inproceedings{9255c8402db445f5b35d6e91186bb27d,
title = "Using HCI task modeling techniques to measure how deeply students model",
abstract = "User modeling in AIED has been extended in the past decades to include affective and motivational aspects of learner's interaction in intelligent tutoring systems. An issue in such systems is researchers' ability to understand and detect students' cognitive and meta-cognitive processes while they learn. In order to study those factors, various detectors have been created that classify episodes in log data as gaming, high/low effort on task, robust learning, etc. When simulating students' learning processes in an ITS, a question remains as to how to create those detectors, and how reliable their simulation of the user's learning processes can be. In this article, we present our method for creating a detector of shallow modeling practices within a meta-tutor instructional system. The detector was defined using HCI (human-computer interaction) task modeling as well as a coding scheme defined by human coders from past users' screen recordings of software use. The detector produced classifications of student behavior that were highly similar to classifications produced by human coders with a kappa of .925.",
keywords = "Human-computer interaction, Intelligent tutoring system, Robust learning, Shallow learning, Task modeling",
author = "Sylvie Girard and Lishan Zhang and Yoalli Hidalgo-Pontet and Kurt VanLehn and Winslow Burleson and Chavez-Echeagary, {Maria Elena} and Javier Gonzalez-Sanchez",
year = "2013",
language = "English (US)",
volume = "1009",
pages = "31--40",
booktitle = "CEUR Workshop Proceedings",
publisher = "CEUR-WS",

}

TY - GEN

T1 - Using HCI task modeling techniques to measure how deeply students model

AU - Girard, Sylvie

AU - Zhang, Lishan

AU - Hidalgo-Pontet, Yoalli

AU - VanLehn, Kurt

AU - Burleson, Winslow

AU - Chavez-Echeagary, Maria Elena

AU - Gonzalez-Sanchez, Javier

PY - 2013

Y1 - 2013

N2 - User modeling in AIED has been extended in the past decades to include affective and motivational aspects of learner's interaction in intelligent tutoring systems. An issue in such systems is researchers' ability to understand and detect students' cognitive and meta-cognitive processes while they learn. In order to study those factors, various detectors have been created that classify episodes in log data as gaming, high/low effort on task, robust learning, etc. When simulating students' learning processes in an ITS, a question remains as to how to create those detectors, and how reliable their simulation of the user's learning processes can be. In this article, we present our method for creating a detector of shallow modeling practices within a meta-tutor instructional system. The detector was defined using HCI (human-computer interaction) task modeling as well as a coding scheme defined by human coders from past users' screen recordings of software use. The detector produced classifications of student behavior that were highly similar to classifications produced by human coders with a kappa of .925.

AB - User modeling in AIED has been extended in the past decades to include affective and motivational aspects of learner's interaction in intelligent tutoring systems. An issue in such systems is researchers' ability to understand and detect students' cognitive and meta-cognitive processes while they learn. In order to study those factors, various detectors have been created that classify episodes in log data as gaming, high/low effort on task, robust learning, etc. When simulating students' learning processes in an ITS, a question remains as to how to create those detectors, and how reliable their simulation of the user's learning processes can be. In this article, we present our method for creating a detector of shallow modeling practices within a meta-tutor instructional system. The detector was defined using HCI (human-computer interaction) task modeling as well as a coding scheme defined by human coders from past users' screen recordings of software use. The detector produced classifications of student behavior that were highly similar to classifications produced by human coders with a kappa of .925.

KW - Human-computer interaction

KW - Intelligent tutoring system

KW - Robust learning

KW - Shallow learning

KW - Task modeling

UR - http://www.scopus.com/inward/record.url?scp=84925018663&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925018663&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84925018663

VL - 1009

SP - 31

EP - 40

BT - CEUR Workshop Proceedings

PB - CEUR-WS

ER -