Dynamic detection of novice vs. skilled use without a task model

Amy Hurst, Scott E. Hudson, Jennifer Mankoff

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

Abstract

If applications were able to detect a user's expertise, then software could automatically adapt to better match exper-tise. Detecting expertise is difficult because a user's skill changes as the user interacts with an application and differs across applications. This means that expertise must be sensed dynamically, continuously, and unobtrusively so as not to burden the user. We present an approach to this prob-lem that can operate without a task model based on low-level mouse and menu data which can typically be sensed across applications at the operating systems level. We have implemented and trained a classifier that can detect "nov-ice" or "skilled" use of an image editing program, the GNU Image Manipulation Program (GIMP), at 91% accuracy, and tested it against real use. In particular, we developed and tested a prototype application that gives the user dy-namic application information that differs depending on her performance.

Original languageEnglish (US)
Title of host publicationProceedings of the SIGCHI Conference on Human Factors in Computing Systems 2007, CHI 2007
Pages271-280
Number of pages10
DOIs
StatePublished - Oct 22 2007
Event25th SIGCHI Conference on Human Factors in Computing Systems 2007, CHI 2007 - San Jose, CA, United States
Duration: Apr 28 2007May 3 2007

Publication series

NameConference on Human Factors in Computing Systems - Proceedings

Other

Other25th SIGCHI Conference on Human Factors in Computing Systems 2007, CHI 2007
CountryUnited States
CitySan Jose, CA
Period4/28/075/3/07

Fingerprint

Ice
Classifiers

Keywords

  • Intelligent user interfaces
  • Statistical models

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design

Cite this

Hurst, A., Hudson, S. E., & Mankoff, J. (2007). Dynamic detection of novice vs. skilled use without a task model. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems 2007, CHI 2007 (pp. 271-280). (Conference on Human Factors in Computing Systems - Proceedings). https://doi.org/10.1145/1240624.1240669

Dynamic detection of novice vs. skilled use without a task model. / Hurst, Amy; Hudson, Scott E.; Mankoff, Jennifer.

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems 2007, CHI 2007. 2007. p. 271-280 (Conference on Human Factors in Computing Systems - Proceedings).

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

Hurst, A, Hudson, SE & Mankoff, J 2007, Dynamic detection of novice vs. skilled use without a task model. in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems 2007, CHI 2007. Conference on Human Factors in Computing Systems - Proceedings, pp. 271-280, 25th SIGCHI Conference on Human Factors in Computing Systems 2007, CHI 2007, San Jose, CA, United States, 4/28/07. https://doi.org/10.1145/1240624.1240669
Hurst A, Hudson SE, Mankoff J. Dynamic detection of novice vs. skilled use without a task model. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems 2007, CHI 2007. 2007. p. 271-280. (Conference on Human Factors in Computing Systems - Proceedings). https://doi.org/10.1145/1240624.1240669
Hurst, Amy ; Hudson, Scott E. ; Mankoff, Jennifer. / Dynamic detection of novice vs. skilled use without a task model. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems 2007, CHI 2007. 2007. pp. 271-280 (Conference on Human Factors in Computing Systems - Proceedings).
@inproceedings{b7149ac9aa374a6c832e97e14c707196,
title = "Dynamic detection of novice vs. skilled use without a task model",
abstract = "If applications were able to detect a user's expertise, then software could automatically adapt to better match exper-tise. Detecting expertise is difficult because a user's skill changes as the user interacts with an application and differs across applications. This means that expertise must be sensed dynamically, continuously, and unobtrusively so as not to burden the user. We present an approach to this prob-lem that can operate without a task model based on low-level mouse and menu data which can typically be sensed across applications at the operating systems level. We have implemented and trained a classifier that can detect {"}nov-ice{"} or {"}skilled{"} use of an image editing program, the GNU Image Manipulation Program (GIMP), at 91{\%} accuracy, and tested it against real use. In particular, we developed and tested a prototype application that gives the user dy-namic application information that differs depending on her performance.",
keywords = "Intelligent user interfaces, Statistical models",
author = "Amy Hurst and Hudson, {Scott E.} and Jennifer Mankoff",
year = "2007",
month = "10",
day = "22",
doi = "10.1145/1240624.1240669",
language = "English (US)",
isbn = "1595935932",
series = "Conference on Human Factors in Computing Systems - Proceedings",
pages = "271--280",
booktitle = "Proceedings of the SIGCHI Conference on Human Factors in Computing Systems 2007, CHI 2007",

}

TY - GEN

T1 - Dynamic detection of novice vs. skilled use without a task model

AU - Hurst, Amy

AU - Hudson, Scott E.

AU - Mankoff, Jennifer

PY - 2007/10/22

Y1 - 2007/10/22

N2 - If applications were able to detect a user's expertise, then software could automatically adapt to better match exper-tise. Detecting expertise is difficult because a user's skill changes as the user interacts with an application and differs across applications. This means that expertise must be sensed dynamically, continuously, and unobtrusively so as not to burden the user. We present an approach to this prob-lem that can operate without a task model based on low-level mouse and menu data which can typically be sensed across applications at the operating systems level. We have implemented and trained a classifier that can detect "nov-ice" or "skilled" use of an image editing program, the GNU Image Manipulation Program (GIMP), at 91% accuracy, and tested it against real use. In particular, we developed and tested a prototype application that gives the user dy-namic application information that differs depending on her performance.

AB - If applications were able to detect a user's expertise, then software could automatically adapt to better match exper-tise. Detecting expertise is difficult because a user's skill changes as the user interacts with an application and differs across applications. This means that expertise must be sensed dynamically, continuously, and unobtrusively so as not to burden the user. We present an approach to this prob-lem that can operate without a task model based on low-level mouse and menu data which can typically be sensed across applications at the operating systems level. We have implemented and trained a classifier that can detect "nov-ice" or "skilled" use of an image editing program, the GNU Image Manipulation Program (GIMP), at 91% accuracy, and tested it against real use. In particular, we developed and tested a prototype application that gives the user dy-namic application information that differs depending on her performance.

KW - Intelligent user interfaces

KW - Statistical models

UR - http://www.scopus.com/inward/record.url?scp=35348923673&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35348923673&partnerID=8YFLogxK

U2 - 10.1145/1240624.1240669

DO - 10.1145/1240624.1240669

M3 - Conference contribution

AN - SCOPUS:35348923673

SN - 1595935932

SN - 9781595935939

T3 - Conference on Human Factors in Computing Systems - Proceedings

SP - 271

EP - 280

BT - Proceedings of the SIGCHI Conference on Human Factors in Computing Systems 2007, CHI 2007

ER -