Toolkit to support intelligibility in context-aware applications
The DOI matches its Crossref record; 44 of the 45 references it cites were found in a registry or an index.
Abstract
Context-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 application decision models. Furthermore, users need different types of explanations and this complicates the implementation of intelligibility. We have developed the Intelligibility Toolkit that makes it easy for application developers to obtain eight types of explanations from the most popular decision models of context-aware applications. We describe its extensible architecture, and the explanation generation algorithms we developed. We validate the usefulness of the toolkit with three canonical applications that use the toolkit to generate explanations for end-users.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“We further identified two new categories that were not covered by the prior works: System Requirements and Impact, and Limitations.”
From Investigating Explainability of Generative AI for Code through Scenario-based Design (2022) · cites this paper as Lim and Dey [53]
In the citing paper
“We adopt a similar definition of Input in Lim and Dey[53], as in what kind of inputs the model can take to generate code.”
From Investigating Explainability of Generative AI for Code through Scenario-based Design (2022) · cites this paper as [53]
Citations
Cites
(1992) · Cited by 23,431
A tutorial on hidden Markov models and selected applications in speech recognition
Rabiner, L. R. (1989) · Proceedings of the IEEE · doi:10.1109/5.18626 · Cited by 22,743 · cited 2×
“and the emission probabilities of the observations given the states ܲሺ ௧ |ݔ ௧ ሻ . For detailed information on HMMs, refer to [ 36 ].”
BackgroundThe WEKA data mining software: an update
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I. H. (2009) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1656274.1656278 · Cited by 17,750
Dey, A. K., Abowd, G. D., & Salber, D. (2001) · Human–Computer Interaction · doi:10.1207/s15327051hci16234_02 · Cited by 2,951 · cited 6×
“INTRODUCTION Context-aware applications [11] make use of sensed inputs and contexts, coupled with intelligent decision-making, in order to automatically and calmly [43] adapt to serve users better.”
BackgroundMethodInfluentialSelf-citationExplaining collaborative filtering recommendations
Herlocker, J. L., Konstan, J. A., & Riedl, J. (2000) · Proceedings of the 2000 ACM conference on Computer supported cooperative work · doi:10.1145/358916.358995 · Cited by 1,731 · cited 1×
“, recommender systems [20], end-user debugging [22], user interfaces [30], user modeling [10]), and been found to improve user trust and acceptance of these applications.”
BackgroundActivity Recognition in the Home Using Simple and Ubiquitous Sensors
Tapia, E. M., Intille, S. S., & Larson, K. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-24646-6_10 · Cited by 1,323 · cited 1×
“Naïve Bayes classifiers have been used to recognize: physical activity ( e.g. , [9]), domestic activity ( e.g. , [39]), interruptibility ( e.g. , [42]).”
Understanding mobility based on GPS data
Zheng, Y., Li, Q., Chen, Y., Xie, X., & Ma, W.-Y. (2008) · Proceedings of the 10th international conference on Ubiquitous computing · doi:10.1145/1409635.1409677 · Cited by 1,132 · cited 1×
“Decision trees are popular in applications to recognize: identity / ability ( e.g. , [8]), interruptibility ( e.g. , [2, 42]), mobility ( e.g. , [45]), etc .”
BackgroundThe Coming Age of Calm Technology
Weiser, M., & Brown, J. S. (1997) · Beyond Calculation · doi:10.1007/978-1-4612-0685-9_6 · Cited by 1,029 · cited 1×
“INTRODUCTION Context-aware applications [11] make use of sensed inputs and contexts, coupled with intelligent decision-making, in order to automatically and calmly [43] adapt to serve users better.”
BackgroundA service‐oriented middleware for building context‐aware services
Gu, T., Pung, H. K., & Zhang, D. Q. (2005) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2004.06.002 · Cited by 887 · cited 1×
“Also, the number of rule-based toolkits for context-aware applications indicates the popularity of rules ( e.g. , [1, 3, 13, 18]).”
BackgroundAccurate activity recognition in a home setting
van Kasteren, T., Noulas, A., Englebienne, G., & Kröse, B. (2008) · Proceedings of the 10th international conference on Ubiquitous computing · doi:10.1145/1409635.1409637 · Cited by 874 · cited 1×
“Home Activity Recognizer – HMM We demonstrate explanations from an HMM model using the dataset from [21] about domestic activity, and train a HMM with a sequence length of 5 min, and 1 min per sequence step.”
MethodMUIR, B. M. (1994) · Ergonomics · doi:10.1080/00140139408964957 · Cited by 873 · cited 1×
“This can frustrate users [4], and cause them to lose trust in the applications [ 29 ].”
BackgroundFroehlich (2009) · doi:10.1145/1518701.1518861 · Cited by 563 · cited 2×
“They are popular in the following domains: activity recognition ( e.g. , [41]), adaptation / personalization ( e.g. , [40]), awareness / monitoring ( e.g. , [12]), reminders ( e.g. , [6]), location guides ( e.g. , [31]), and persuasion ( e.g. , [16]).”
BackgroundWhy and why not explanations improve the intelligibility of context-aware intelligent systems
Lim, B. Y., Dey, A. K., & Avrahami, D. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1519023 · Cited by 552 · cited 3×
“To counter this, it is important to make context-aware applications intelligible [5, 25, 26] by automatically providing explanations of application behavior.”
BackgroundSelf-citationExplanations From Intelligent Systems: Theoretical Foundations and Implications for Practice1
Gregor, S., & Benbasat, I. (1999) · MIS Quarterly · doi:10.2307/249487 · Cited by 535 · cited 1×
“, [17, 23, 26, 27]) and specifically, Lim & Dey [25] describe a set of ten explanation types that context-aware applications should provide for end-users.”
BackgroundIntelligibility and Accountability: Human Considerations in Context-Aware Systems
Bellotti, V., & Edwards, K. (2001) · Human–Computer Interaction · doi:10.1207/s15327051hci16234_05 · Cited by 471 · cited 1×
“To counter this, it is important to make context-aware applications intelligible [5, 25, 26] by automatically providing explanations of application behavior.”
BackgroundActiveBelt: Belt-Type Wearable Tactile Display for Directional Navigation
Tsukada, K., & Yasumura, M. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-30119-6_23 · Cited by 312 · cited 1×
“, [41]), adaptation / personalization (e.”
Bardram, J. E. (2005) · Lecture Notes in Computer Science · doi:10.1007/11428572_7 · Cited by 312 · cited 1×
“Also, the number of rule-based toolkits for context-aware applications indicates the popularity of rules ( e.g. , [1, 3, 13, 18]).”
BackgroundIs Context-Aware Computing Taking Control away from the User? Three Levels of Interactivity Examined
Barkhuus, L., & Dey, A. (2003) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-39653-6_12 · Cited by 303 · cited 1×
“This can frustrate users [4], and cause them to lose trust in the applications [29].”
BackgroundSelf-citationExplaining Classifications For Individual Instances
Robnik-Sikonja, M., & Kononenko, I. (2008) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2007.190734 · Cited by 254 · cited 1×
“, competing methods to explain naïve Bayes are presented in [28, 34, 37]); (b) new model types (e.”
MethodAssessing demand for intelligibility in context-aware applications
Lim, B. Y., & Dey, A. K. (2009) · Proceedings of the 11th international conference on Ubiquitous computing · doi:10.1145/1620545.1620576 · Cited by 246 · cited 7×
“(1) An architecture for generating a wide range of explanations drawn from Lim & Dey [25], including Why, Why Not, How To, What, What If, Inputs, Outputs and Certainty.”
BackgroundMethodInfluentialSelf-citationEvaluating user interface systems research
Olsen, D. R. (2007) · Proceedings of the 20th annual ACM symposium on User interface software and technology · doi:10.1145/1294211.1294256 · Cited by 234 · cited 2×
“The toolkit is designed to satisfy requirements inspired from Olsen's writings about infrastructure evaluation [32]:”
BackgroundMethodInteracting meaningfully with machine learning systems: Three experiments
Stumpf, S., Rajaram, V., Li, L., Wong, W.-K., Burnett, M., Dietterich, T., Sullivan, E., & Herlocker, J. (2009) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2009.03.004 · Cited by 184 · cited 1×
“, [38]), we built different applications for each model type to demonstrate the generality of the Intelligibility Toolkit to provide explanations across application domains.”
MethodRobust Recognition of Reading Activity in Transit Using Wearable Electrooculography
Bulling, A., Ward, J. A., Gellersen, H. W., & Tröster, G. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-79576-6_2 · Cited by 141 · cited 1×
“HMMs have been used to model: physical ( e.g. , [9]) and domestic activity ( e.g. , [21]), gaze ( e.g. , [7]).”
MethodFrom awareness to connectedness: the design and deployment of presence displays
Dey, A. K., & Guzman, E. S. D. (2006) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/1124772.1124905 · Cited by 139
Self-citationHow it works: a field study of non-technical users interacting with an intelligent system
Tullio, J., Dey, A. K., Chalecki, J., & Fogarty, J. (2007) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1240624.1240630 · Cited by 137 · cited 1×
“[42] explained interruptibility inferred from decision trees and naïve Bayes with What explanations.”
MethodSelf-citationNomograms for Visualization of Naive Bayesian Classifier
Možina, M., Demšar, J., Kattan, M. W., & Zupan, B. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-30116-5_32 · Cited by 133 · cited 1×
“, competing methods to explain naïve Bayes are presented in [28, 34, 37]); (b) new model types (e.”
MethodVisual explanation of evidence in additive classifiers
Poulin, B., Eisner, R., Szafron, D., Lu, P., Greiner, R., Wishart, D. S., Fyshe, A., Pearcy, B., Macdonell, C., & Anvik, J. (2006) · NPARC · Cited by 131
Investigating statistical machine learning as a tool for software development
Patel, K., Fogarty, J., Landay, J. A., & Harrison, B. (2008) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1357054.1357160 · Cited by 129 · cited 1×
“Although important [33], the toolkit does not currently capture and explain these preFigure 7: IM Autostatus.”
BackgroundTracking Free-Weight Exercises
Chang, K.-H., Chen, M. Y., & Canny, J. (2008) · Cited by 126
Answering why and why not questions in user interfaces
Myers, B. A., Weitzman, D. A., Ko, A. J., & Chau, D. H. (2006) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1124772.1124832 · Cited by 126 · cited 2×
“The Crystal framework [30] supports only Why / Why Not explanations for desktop-based applications to explain themselves through Command Objects.”
BackgroundFinding causes of program output with the Java Whyline
Ko, A. J., & Myers, B. A. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1518942 · Cited by 123 · cited 2×
“The Whyline [22] similarly explains Why / Why Not to end-user programmers, by examining the program execution tree.”
BackgroundPersonisAD: Distributed, Active, Scrutable Model Framework for Context-Aware Services
Assad, M., Carmichael, D. J., Kay, J., & Kummerfeld, B. (2007) · Springer eBooks · doi:10.1007/978-3-540-72037-9_4 · Cited by 104 · cited 1×
“PersonisAD [1] defines a distributed framework to support What explanations by resolving identities and associations of devices, locations, people, etc.”
BackgroundResponsiveness in instant messaging: predictive models supporting inter-personal communication
Avrahami, D., & Hudson, S. E. (2006) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1124772.1124881 · Cited by 84 · cited 2×
“We built an AIM plugin that predicts when a buddy will respond to a message (Figure 7). It is trained on an existing dataset from [ 2 ] to build a decision tree.”
BackgroundMethodMobile computing in the retail arena
Newcomb, E., Pashley, T., & Stasko, J. (2003) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/642611.642670 · Cited by 83
Fixing the program my computer learned: barriers for end users, challenges for the machine
Kulesza, T., Wong, W.-K., Stumpf, S., Perona, S., White, R., Burnett, M. M., Oberst, I., & Ko, A. J. (2009) · Proceedings of the 14th international conference on Intelligent user interfaces · doi:10.1145/1502650.1502678 · Cited by 83 · cited 1×
“[24] built an intelligible email sorter that uses naïve Bayes for classification.”
MethodKofod‐Petersen, A., & Marius Mikalsen, A. (2005) · Revue d intelligence artificielle · doi:10.3166/ria.19.479-498 · Cited by 82
Support for context-aware intelligibility and control
Dey, A. K., & Newberger, A. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1518832 · Cited by 82 · cited 5×
“The most similar framework to our toolkit is the Enactor framework [13], on which we base our Intelligibility Toolkit.”
BackgroundMethodInfluentialSelf-citationCheverst, K., Byun, H. E., Fitton, D., Sas, C., Kray, C., & Villar, N. (2005) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-005-1269-8 · Cited by 81
Reminding About Tagged Objects Using Passive RFIDs
Borriello, G., Brunette, W., Hall, M., Hartung, C., & Tangney, C. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-30119-6_3 · Cited by 63
Inferring Identity Using Accelerometers in Television Remote Controls
Chang, K.-H., Hightower, J. R., & Kveton, B. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-01516-8_11 · Cited by 47 · cited 1×
“Decision trees are popular in applications to recognize: identity / ability ( e.g. , [8]), interruptibility ( e.g. , [2, 42]), mobility ( e.g. , [45]), etc .”
BackgroundToolkit support for developing and deploying sensor-based statistical models of human situations
Fogarty, J., & Hudson, S. E. (2007) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1240624.1240645 · Cited by 46 · cited 1×
“Create a Widget that tracks and updates all input features (extracted from the Subtle toolkit [14]).”
BackgroundUbiquitous Chip: A Rule-Based I/O Control Device for Ubiquitous Computing
Terada, T., Tsukamoto, M., Hayakawa, K., Yoshihisa, T., Kishino, Y., Kashitani, A., & Nishio, S. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24646-6_18 · Cited by 32 · cited 1×
“They are popular in the following domains: activity recognition ( e.g. , [41]), adaptation / personalization ( e.g. , [40]), awareness / monitoring ( e.g. , [12]), reminders ( e.g. , [6]), location guides ( e.g. , [31]), and persuasion ( e.g. , [16]).”
A Categorization of Explanation Questions for Task Processing Systems.
McGuinness, D. L., Glass, A., Wolverton, M. J., & da Silva, P. P. (2007) · Cited by 12
Specification and Verification of Complex Location Events with Panoramic
Welbourne, E., Bałazińska, M., Borriello, G., & Fogarty, J. A. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-12654-3_4 · Cited by 12
Research works printed but not linked: 1
- }} Franois , J.M. ( 2010 ). Jahmm: An implementation of Hidden Markov Models in Java . http://code.google.com/p/jahmm/. Retrieved 9 Mar 2010. }}Franois, J.M. (2010). Jahmm: An implementation of Hidden Markov Models in Java. http://code.google.com/p/jahmm/. Retrieved 9 Mar 2010.
Cited by
Context Aware Computing for The Internet of Things: A Survey
Perera, C., Zaslavsky, A., Christen, P., & Georgakopoulos, D. (2014) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2013.042313.00197 · Cited by 2,861
“We present the results of a survey conducted by Lim and Dey [108] in Figure 7.”
BackgroundMethodInfluentialQuestioning the AI: Informing Design Practices for Explainable AI User Experiences
Liao, Q. V., Gruen, D., & Miller, S. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376590 · Cited by 925
“We added three more types based on [44, 55, 56]– questions regarding model Input (training data), Output, and Performance.”
BackgroundMethodInfluentialDesigning Theory-Driven User-Centric Explainable AI
Wang, D., Yang, Q., Abdul, A., & Lim, B. Y. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300831 · Cited by 906
“Lim and Dey identified several queries (called intelligibility queries) that a user may ask of a smart system [65, 66].”
BackgroundSelf-citationAbdul, A., Vermeulen, J., Wang, D., Lim, B. Y., & Kankanhalli, M. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174156 · Cited by 743
“…have been proposed to aid the development of explainable ambient intelligence: PersonisAD for scrutable personalization [8], Per-sonisLF for long-term user models with forgetting [10], En-cators to explain context reasoning [41], and the Intelligibility Toolkit to explain question types [113].”
BackgroundInfluentialSelf-citationVaithilingam, P., Zhang, T., & Glassman, E. L. (2022) · CHI Conference on Human Factors in Computing Systems Extended Abstracts · doi:10.1145/3491101.3519665 · Cited by 660
Metadata
- Authors
- Lim, B. Y., & Dey, A. K.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- Proceedings of the 12th ACM international conference on Ubiquitous computing
- Publisher
- ACM
- Published
- 2010-09-26
- Pages
- 13-22
- OpenAlex
- W1990992533
- Cited by
- 143
- References
- 45
- Citations by year
- 2026: 5 · 2025: 5 · 2024: 8 · 2023: 11 · 2022: 9 · 2021: 13 · 2020: 12 · 2019: 10 · 2018: 11 · 2017: 7 · 2016: 11 · 2015: 5 · 2014: 3 · 2013: 8 · 2012: 14
- FWCI
- 8.53
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) (publishedVersion)
- Funders
- National Science Foundation
- Agency for Science, Technology and Research
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- 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
- context-aware systems, intelligibility, explainable AI, explanation generation, decision models, user understanding
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.