Brian Y. Lim
ABSTRACT
Since context-aware applications use implicit sensing and increasingly complex decision making, they may make mistakes or users may misunderstand their actions. This may hinder trust and adoption of context-aware applications. We hypothesize that making these applications intelligible by explaining themselves to users would help counter this lack of trust. The proposed thesis would contribute to context-aware computing by (i) understanding the need to explain these applications to users, (ii) understanding the benefits and trade-offs of providing intelligibility, and (iii) providing toolkit support intelligibility to ultimately improve the trust, adoption of, and sustained use context-aware systems.
- }}Assad, M. et al. (2007). PersonisAD: Distributed, Active, Scrutable Model Framework for Context-Aware Services. Pervasive 07, 55--72. Google Scholar
Digital Library
- }}Bellotti, V. & Edwards, W.K. (2001). Intelligibility and Accountability: Human Considerations in Context-Aware Systems, Human-Computer Interaction, 16(2-4): 193--212. Google ScholarDigital Library
- }}Cassens, J. (2008). Explanation Awareness and Ambient Intelligence as Social Technologies. Ph.D. thesis.Google Scholar
- }}Cheverst, K.. et al. (2005). Exploring issues of user model transparency and proactive behavior in an office environment control system. UMUAI 05, 15(3-4), 235--273. Google ScholarDigital Library
- }}Dey, A.K., Abowd, G.D. & Salber, D. (2001). A conceptual framework and a toolkit for supporting the rapid prototyping of context-aware applications. Human-Computer Interaction, 16(2-4): 97--166. Google ScholarDigital Library
- }}Dey, A. K. & Newberger, A. (2009). Support for context-aware intelligibility and control. CHI 09, 859--868. Google ScholarDigital Library
- }}Ko, A. J. & Myers, B. A. (2009). Finding causes of program output with the Java Whyline. CHI 09, 1569--1578. Google ScholarDigital Library
- }}Kuleza, T. et al. (2009). Fixing the Program My Computer Learned: Barriers for Users, Challenges for the Machine. IUI 09, 187--196. Google ScholarDigital Library
- }}Lim, B. Y., Dey, A. K. & Avrahami, D. (2009). Why and why not explanations improve the intelligibility of context-aware intelligent systems. CHI 09, 2119--2128. Google ScholarDigital Library
- }}Lim, B. Y., Dey, A. K. (2009). Assessing Demand for Intelligibility in Context-Aware Applications. Ubicomp 09, 195--204. Google ScholarDigital Library
- }}1Lim, B. Y., & Dey, A. K. (2010). Toolkit to Support Intelligibility in Context-Aware Applications. To appear in Ubicomp 10. Google ScholarDigital Library
- }}Tullio, J. et al. (2007). How it works: A field study of non-technical users interacting with an intelligent system. CHI 07, 31--40. Google ScholarDigital Library
Index Terms
- Improving trust in context-aware applications with intelligibility
Recommendations
Why and why not explanations improve the intelligibility of context-aware intelligent systems
CHI '09: Proceedings of the SIGCHI Conference on Human Factors in Computing SystemsContext-aware intelligent systems employ implicit inputs, and make decisions based on complex rules and machine learning models that are rarely clear to users. Such lack of system intelligibility can lead to loss of user trust, satisfaction and ...
Toolkit to support intelligibility in context-aware applications
UbiComp '10: Proceedings of the 12th ACM international conference on Ubiquitous computingContext-aware applications should be intelligible so users can better understand how they work and improve their trust in them. However, providing intelligibility is non-trivial and requires the developer to understand how to generate explanations from ...
Assessing demand for intelligibility in context-aware applications
UbiComp '09: Proceedings of the 11th international conference on Ubiquitous computingIntelligibility can help expose the inner workings and inputs of context-aware applications that tend to be opaque to users due to their implicit sensing and actions. However, users may not be interested in all the information that the applications can ...
Comments