Switch detector: an activity spotting system for desktop
Abstract
An average white-collar worker deals with enormous amount of digital information on daily basis. Recently, there has been a growing interest to support their work. However, in order to be really supportive there is a need to know the current activity of the user at all times. In this paper we present a new technique that takes advantage of temporal aspects of user activity behavior to infer when it is most likely that an activity switch is occurring. We then describe "Activity Switch Detector" an interactive switch notification system embodying these ideas, and an extensive user study by ten participants to test the validity of the approach and present its results.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
It is very challenging to achieve high prediction accuracy of task switches without too many false positives.
“the results show that it is very challenging to achieve high prediction accuracy of task switches without too many false positives [15], [16], [17]”
From Detecting Developers' Task Switches and Types (2022) · cites this paper as [15]
The user interface used to collect ground truth for task switches and types resembles the one by Mirza et al.
“The user interface we used to collect the ground truth for task switches and types resembles the one by Mirza et al. [15], [25], [33].”
From Detecting Developers' Task Switches and Types (2022) · cites this paper as [15]
Previous research has shown that detecting task switches is difficult, even for very short periods of time and in controlled environments.
“Overall, previous research has shown that detecting task switches is difficult, even for very short periods of time and in controlled environments.”
From Detecting Developers' Task Switches and Types (2022) · cites this paper as [15]
Switching to another application might be another indication for a task switch.
“Since switching to another application might be another indication for a task switch [15], [47], we added one feature that captures these.”
From Detecting Developers' Task Switches and Types (2022) · cites this paper as [15]
Mirza et al. relaxed the constraint of a fixed time window, used adjusted frequency averages and studied the various approaches with 10 graduate students; they found that their approach improved the accuracy and achieved an overall accuracy of 58 percent.
“Mirza et al. [15] relaxed the constraint of a fixed time window, used adjusted frequency averages and studied the various approaches with 10 graduate students. They found that their approach improved the accuracy and achieved an overall accuracy of 58 percent.”
From Detecting Developers' Task Switches and Types (2022) · cites this paper as [15]
The classifier can make predictions even on previously unseen applications, distinguishing it from previous work.
“One important aspect of our approach that distinguishes our classifier from previous work (e.g., [15], [22], [47]) is its ability to make predictions even on previously unseen applications.”
From Detecting Developers' Task Switches and Types (2022) · cites this paper as [15]
Cites
Proceedings of the International Joint Conference on Artificial Intelligence 2007
Bundy, A. (2007) · International Joint Conference on Artificial Intelligence · Cited by 2,761 · see citing works
Witten, I. H., Paynter, G. W., Frank, E., Gutwin, C. A., & Nevill-Manning, C. G. (1999) · doi:10.1145/313238.313437 · Cited by 860 · see citing works
SWISH: semantic analysis of window titles and switching history
Oliver, N., Smith, G., Thakkar, C., & Surendran, A. C. (2006) · Proceedings of the 11th international conference on Intelligent user interfaces · doi:10.1145/1111449.1111492 · Cited by 89 · see citing works
Detecting and correcting user activity switches: algorithms and interfaces
Shen, J., Irvine, J., Bao, X., Goodman, M., Kolibaba, S., Tran, A., Carl, F., Kirschner, B., Stumpf, S., & Dietterich, T. G. (2009) · Proceedings of the 14th international conference on Intelligent user interfaces · doi:10.1145/1502650.1502670 · Cited by 37 · see citing works
Real-time detection of task switches of desktop users
Shen, J., Li, L., & Dietterich, T. G. (2007) · Cited by 28 · see citing works
Evaluating Personal Information Management Using an Activity Logs Enriched Desktop Dataset
Chernov, S., Demartini, G., Herder, E., et al. (2008) · Cited by 25 · see citing works
(2005) · Cited by 14 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Züger, M., Müller, S. C., Meyer, A. N., & Fritz, T. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174165 · Cited by 66 · see citing works
Detecting Developers' Task Switches and Types
Meyer, A. N., Satterfield, C., Zuger, M., Kevic, K., Murphy, G. C., Zimmermann, T., & Fritz, T. (2022) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2020.2984086 · Cited by 14 · see citing works
“Application categories considered: CodeReview [PS], DeveloperTool [3], IDE [3], Idle [PS], [35], IM [PS], [47], Mail [PS], [47], Music [PS], [15], [22], [47], Navigate, Read/Write Document [3], TestingTool [3], Utility, WebBrowser [PS], [3], Unknown 28.”
BackgroundMethodInfluentialA Study on Automatic Classification of Users’ Desktop Interactions
Mirza, H. T., Chen, L., Hussain, I., Majid, A., & Chen, G. (2015) · Cybernetics and Systems · doi:10.1080/01969722.2015.1012372 · Cited by 8 · see citing works
Self-citation
- Authors
- Mirza, H. T., Chen, L., Chen, G., Hussain, I., & He, X.
- Affiliations
- Zhejiang University (CN)
- Venue
- Proceedings of the 20th ACM international conference on Information and knowledge management
- Publisher
- ACM
- Published
- 2011-10-24
- Pages
- 2285-2288
- ISSN
- 2155-0751 (ISSN-L)
- OpenAlex
- W2008484478
- Cited by
- 5
- References
- 7
- Citations by year
- 2020: 2 · 2018: 1 · 2015: 1 · 2014: 1
- FWCI
- 0.73
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Conference on Information and Knowledge Management (CIKM) (publishedVersion)
- Topics
- Social Sciences › Decision Sciences › Information Systems and Management › Personal Information Management and User Behavior
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- temporal analysis, white-collar workers, activity inference, user study
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
