TY - GEN
T1 - On improving application utility prediction
AU - Hailpern, Joshua
AU - Jitkoff, Nicholas
AU - Subida, Joseph
AU - Karahalios, Karrie
PY - 2010
Y1 - 2010
N2 - When using the computer, each user has some notion that "these applications are important" at a given point in time. We term this subset of applications that the user values as high-utility applications. Identifying these high-utility applications is critical to the fields of Task Analysis, User Interruptions, Workflow Analysis, and Goal Prediction. Yet, existing techniques to identify high-utility applications are based upon task identification, conglomeration of related windows, limited qualitative observation, or common sense. Our work directly associates measurable computer interaction (CPU consumption, window area, etc.) with the user's perceived application utility. In this paper, we present an objective utility function that accurately predicts the user's subjective impressions of application importance. Our work is based upon 321 hours of real-world data from 22 users (both professional and academic) improving existing techniques by over 53%.
AB - When using the computer, each user has some notion that "these applications are important" at a given point in time. We term this subset of applications that the user values as high-utility applications. Identifying these high-utility applications is critical to the fields of Task Analysis, User Interruptions, Workflow Analysis, and Goal Prediction. Yet, existing techniques to identify high-utility applications are based upon task identification, conglomeration of related windows, limited qualitative observation, or common sense. Our work directly associates measurable computer interaction (CPU consumption, window area, etc.) with the user's perceived application utility. In this paper, we present an objective utility function that accurately predicts the user's subjective impressions of application importance. Our work is based upon 321 hours of real-world data from 22 users (both professional and academic) improving existing techniques by over 53%.
KW - Application importance
KW - Application utility
KW - Modeling
UR - http://www.scopus.com/inward/record.url?scp=77953099226&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77953099226&partnerID=8YFLogxK
U2 - 10.1145/1753846.1753995
DO - 10.1145/1753846.1753995
M3 - Conference contribution
AN - SCOPUS:77953099226
SN - 9781605589312
T3 - Conference on Human Factors in Computing Systems - Proceedings
SP - 3421
EP - 3426
BT - CHI 2010 - The 28th Annual CHI Conference on Human Factors in Computing Systems, Conference Proceedings and Extended Abstracts
T2 - 28th Annual CHI Conference on Human Factors in Computing Systems, CHI 2010
Y2 - 10 April 2010 through 15 April 2010
ER -