skip to main content
article

Predicting human interruptibility with sensors

Published: 01 March 2005 Publication History

Abstract

A person seeking another person's attention is normally able to quickly assess how interruptible the other person currently is. Such assessments allow behavior that we consider natural, socially appropriate, or simply polite. This is in sharp contrast to current computer and communication systems, which are largely unaware of the social situations surrounding their usage and the impact that their actions have on these situations. If systems could model human interruptibility, they could use this information to negotiate interruptions at appropriate times, thus improving human computer interaction.This article presents a series of studies that quantitatively demonstrate that simple sensors can support the construction of models that estimate human interruptibility as well as people do. These models can be constructed without using complex sensors, such as vision-based techniques, and therefore their use in everyday office environments is both practical and affordable. Although currently based on a demographically limited sample, our results indicate a substantial opportunity for future research to validate these results over larger groups of office workers. Our results also motivate the development of systems that use these models to negotiate interruptions at socially appropriate times.

References

[1]
Barker, R. G. 1968. Ecological Psychology. Stanford University Press.
[2]
Begole, J. B., Tang, J. C., and Hill, R. 2003. Rhythm modeling, visualizations, and applications. In Proceedings of the ACM Symposium on User Interface Software and Technology (UIST 2003). 11--20.
[3]
Begole, J. B., Tang, J. C., Smith, R. B., and Yankelovich, N. 2002. Work rhythms: Analyzing visualizations of awareness histories of distributed groups. In Proceedings of the ACM Conference on Computer Supported Cooperative Work (CSCW 2002). 334--343.
[4]
Bellotti, V. and Edwards, K. 2001. Intelligibility and accountability: Human considerations in context-aware systems. Hum.-Comput. Interact. 16, 2-4, 193--212.
[5]
Burges, C. J. C. 1998. A tutorial on support vector machines for pattern recognition. Data Mining Knowl. Disc. 2, 2, 121--167.
[6]
CMU Sphinx: Open Source Speech Recognition. http://www.speech.cs.cmu.edu/sphinx/.
[7]
Cutrell, E., Czerwinski, M., and Horvitz, E. 2001. Notification, disruption, and memory: Effects of messaging interruptions on memory and performance. In Proceedings of the IFIP Conference on Human-Computer Interaction (INTERACT 2001). 263--269.
[8]
Czerwinski, M., Cutrell, E., and Horvitz, E. 2000a. Instant messaging and interruptions: Influence of task type on performance. In Proceedings of the Australian Conference on Computer-Human Interaction (OZCHI 2000). 356--361.
[9]
Czerwinski, M., Cutrell, E., and Horvitz, E. 2000b. Instant messaging: Effects of relevance and time. In Proceedings of the British HCI Group Annual Conference (HCI 2000). 71--76.
[10]
Dahlböck, N., Jönsson, A., and Ahrenberg, L. 1993. Wizard of Oz studies---Why and how. In Proceedings of the International Conference on Intelligent User Interfaces (IUI 1993). 193--200.
[11]
Duda, R. O. and Hart, P. E. 1973. Pattern Classification and Scene Analysis. John Wiley and Sons.
[12]
Erickson, T. and Kellogg, W. A. 2000. Social translucence: An approach to designing systems that support social processes. ACM Trans. Comput.-Hum. Interact. (TOCHI) 7, 1, 59--83.
[13]
Feldman-Barrett, L. and Barrett, D. J. 2001. Computerized experience-sampling: How technology facilitates the study of conscious experience. Soc. Sci. Comput. Rev. 19, 175--185.
[14]
Fogarty, J., Forlizzi, J., and Hudson, S. E. 2001. Aesthetic information collages: Generating decorative displays that contain information. In Proceedings of the ACM Symposium on User Interface Software and Technology (UIST 2001). 141--150.
[15]
Fogarty, J., Hudson, S., and Lai, J. 2004a. Examining the robustness of sensor-based statistical models of human interruptibility. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2004). 207--214.
[16]
Fogarty, J., Lai, J., and Christensen, J. 2004b. Presence versus availability: The design and evaluation of a context-aware communication client. Int. J. Hum.-Comput. Stud. (IJHCS) 61, 3.
[17]
Freund, Y. and Schapire, R. 1997. A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55, 1, 119--139.
[18]
Goffmann, E. 1982. On Facework. Interaction Ritual, E. Goffmann, Ed. Random House, New York, 5--45.
[19]
Hall, M. A. 2000. Correlation-based feature selection for discrete and numeric class machine learning. In Proceedings of the International Conference on Machine Learning (ICML 2000). 359--366.
[20]
Hatch, M. J. 1987. Physical barriers, task characteristics, and interaction activity in research and development firms. Admin. Sci. Quart. 32, 387--399.
[21]
Heiner, J. M., Hudson, S. E., and Tanaka, K. 1999. The information percolator: Ambient information display in a decorative object. In Proceedings of the ACM Symposium on User Interface Software and Technology (UIST 1999). 141--148.
[22]
Horvitz, E. 1999. Principles of mixed-initiative user interfaces. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 1999).
[23]
Horvitz, E. and Apacible, J. 2003. Learning and reasoning about interruption. In Proceedings of the International Conference on Multimodal Interfaces (ICMI 2003). 20--27.
[24]
Horvitz, E., Breese, J., Heckerman, D., Hovel, D., and Rommelse, K. 1998. The lumiere project: Bayesian user modeling for inferring the goals and needs of software users. In Proceedings of the Conference on Uncertainty and Artificial Intelligence (UAI 1998). 256--265.
[25]
Horvitz, E., Jacobs, A., and Hovel, D. 1999. Attention-sensitive alerting. In Proceeding of the Conference on Uncertainty and Artificial Intelligence (UAI 1999). 305--313.
[26]
Hudson, J. M., Christensen, J., Kellogg, W. A., and Erickson, T. 2002. “I'd be overwhelmed, but it's just one more thing to do”: Availability and interruption in research management. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2002). 97--104.
[27]
Hudson, S., Fogarty, J., Atkeson, C., Avrahami, D., Forlizzi, J., Kiesler, S., Lee, J., and Yang, J. 2003. Predicting human interruptibility with sensors: A wizard of Oz feasibility study. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2003). 257--264.
[28]
Kohavi, R. and John, G. H. 1997. Wrappers for feature subset selection. Artif. Intel. 97, 1--2, 273--324.
[29]
Langley, P. and Sage, S. 1994. Induction of selected Bayesian classifiers. In Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI 1994). 399--406.
[30]
Lu, L., Zhang, H., and Jiang, H. 2002. Content analysis for audio classification and segmentation. IEEE Trans. Speech Audio Process. 10, 7, 504--516.
[31]
Maulsby, D., Greenberg, S., and Mander, R. 1993. Prototyping an intelligent agent through wizard of Oz. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 1993).
[32]
McFarlane, D. C. 2002. Comparison of four primary methods for coordinating the interruption of people in human-computer interaction. Hum.-Comput. Interact. 17, 1, 63--139.
[33]
McFarlane, D. C. 1999. Coordinating the interruption of people in human-computer interaction. In Proceedings of the IFIP Conference on Human-Computer Interaction (INTERACT 1999).
[34]
Milewski, A. E. and Smith, T. M. 2000. Providing presence cues to telephone users. In Proceedings of the ACM Conference on Computer Supported Cooperative Work (CSCW 2000). 89--96.
[35]
Mitchell, T. M. 1997. Machine Learning. McGraw-Hill.
[36]
Oliver, N., Horvitz, E., and Garg, A. 2002. Layered representations for recognizing office activity. In Proceedings of the International Conference on Multimodal Interaction (ICMI 2002). 3--8.
[37]
Perlow, L. A. 1999. The time famine: Toward a sociology of work time. In Admin. Sci. Quart. 44, 1, 57--81.
[38]
Quinlan, J. R. 1993. C4.5: Programs for Machine Learning. Morgan Kaufmann.
[39]
Redström, J., Skog, T., and Hallnäs, L. 2000. Informative art: Using amplified artworks as information displays. In Proceedings of Designing Augmented Reality Environments.
[40]
Schmidt, A., Takaluoma, A., and Mäntyjärvi, J. 2000. Context-aware telephony over WAP. Pers. Ubiquit. Comput. 4, 4, 225--229.
[41]
Seshadri, S. and Shapira, Z. 2001. Managerial allocation of time and effort: The effects of interruptions. Manage. Sci. 47, 5, 647--662.
[42]
Voida, A., Newstetter, W. C., and Mynatt, E. D. 2002. When conventions collide: The tensions of instant messaging attributed. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2002). 187--194.
[43]
Witten, I. H. and Frank, E. 1999. Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann.

Cited By

View all
  • (2024)How Do Data Analysts Respond to AI Assistance? A Wizard-of-Oz StudyProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3641891(1-22)Online publication date: 11-May-2024
  • (2023)AI-to-Human ActuationProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/35808127:1(1-32)Online publication date: 28-Mar-2023
  • (2023)Design and Field Trial of Tunee in Shared Houses: Exploring Experiences of Sharing Individuals’ Current Noise-level Preferences with HousematesProceedings of the 2023 CHI Conference on Human Factors in Computing Systems10.1145/3544548.3581521(1-15)Online publication date: 19-Apr-2023
  • Show More Cited By

Recommendations

Reviews

Claudia Roda

How can a system decide whether it is appropriate to interrupt a person's activity to report, for example, the availability of new information, or the arrival of an email or phone call__?__ The authors of this paper argue "that simple sensors can support the construction of models that estimate human interruptibility as well as people do." They support their claim with a very detailed description of a set of quantitative studies, analyzing audio and video recordings of people in their working environments, along with their self-reported "rate of current interruptibility." The results obtained from a set of manually simulated sensors detecting various activities in the environment are used to feed models (based on standard machine learning techniques) capable of providing estimates of interruptibility. The authors demonstrate that these estimates "are as good as or better than the estimates provided by people watching [the] audio and video recordings." While the authors are mainly interested in demonstrating that interruptibility can be estimated using easy-to-build sensors, the reader will have to turn to other sources for a more holistic view of human interruptibility. Such a holistic view would address, for example, the issues of a person's goals with respect to the interruption [1]; the situation in which the interruption takes place, and individual preferences with respect to interruptions [2]; and the fine timing of interruptions during task performance. The results and methodologies described in this paper will be very relevant for those studying sensor-based detection of human cognitive states. Online Computing Reviews Service

Access critical reviews of Computing literature here

Become a reviewer for Computing Reviews.

Comments

Information & Contributors

Information

Published In

cover image ACM Transactions on Computer-Human Interaction
ACM Transactions on Computer-Human Interaction  Volume 12, Issue 1
March 2005
146 pages
ISSN:1073-0516
EISSN:1557-7325
DOI:10.1145/1057237
Issue’s Table of Contents

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 March 2005
Published in TOCHI Volume 12, Issue 1

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Situationally appropriate interaction
  2. context-aware computing
  3. machine learning
  4. managing human attention
  5. sensor-based interfaces

Qualifiers

  • Article

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)90
  • Downloads (Last 6 weeks)6
Reflects downloads up to 27 Jan 2025

Other Metrics

Citations

Cited By

View all
  • (2024)How Do Data Analysts Respond to AI Assistance? A Wizard-of-Oz StudyProceedings of the 2024 CHI Conference on Human Factors in Computing Systems10.1145/3613904.3641891(1-22)Online publication date: 11-May-2024
  • (2023)AI-to-Human ActuationProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/35808127:1(1-32)Online publication date: 28-Mar-2023
  • (2023)Design and Field Trial of Tunee in Shared Houses: Exploring Experiences of Sharing Individuals’ Current Noise-level Preferences with HousematesProceedings of the 2023 CHI Conference on Human Factors in Computing Systems10.1145/3544548.3581521(1-15)Online publication date: 19-Apr-2023
  • (2023)XAIR: A Framework of Explainable AI in Augmented RealityProceedings of the 2023 CHI Conference on Human Factors in Computing Systems10.1145/3544548.3581500(1-30)Online publication date: 19-Apr-2023
  • (2023)Stop Bad Real-time Feedback!: Estimation of the Timing of Feedback that Negatively Impacts Presenters for Presentation Training in Virtual Reality2023 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)10.1109/ISMAR-Adjunct60411.2023.00087(405-410)Online publication date: 16-Oct-2023
  • (2023)A Survey on When to Think About Talking to Users of the Work Immersion Time Presentation System in the OfficeHuman-Computer Interaction10.1007/978-3-031-35602-5_33(465-476)Online publication date: 23-Jul-2023
  • (2022)Designing PairBuddy—A Conversational Agent for Pair ProgrammingACM Transactions on Computer-Human Interaction10.1145/349832629:4(1-44)Online publication date: 5-May-2022
  • (2022)An automated system recommending background music to listen to while workingUser Modeling and User-Adapted Interaction10.1007/s11257-022-09325-y32:3(355-388)Online publication date: 1-Jul-2022
  • (2021)Designing Procedure Execution Tools with Emerging Technologies for Future AstronautsApplied Sciences10.3390/app1104160711:4(1607)Online publication date: 10-Feb-2021
  • (2021)Learning When Agents Can Talk to Drivers Using the INAGT Dataset and Multisensor FusionProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/34781255:3(1-28)Online publication date: 14-Sep-2021
  • Show More Cited By

View Options

Login options

Full Access

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media