Improving Understanding and Trust with Intelligibility in Context-Aware Applications

To facilitate everyday activities, context-aware applications use sensors to detect what is happening and use increasingly complex mechanisms ( e.g., by using big rule-sets or machine learning) to infer the user's context and intent. For example, a mobile application can recognize that the user is in a conversation and suppress any incoming calls. When the application works well, this implicit sensing and complex inference remain invisible. However, when it behaves inappropriately or unexpectedly, users may not understand its behavior. This can lead users to mistrust, misuse, or even abandon it. To counter this lack of understanding and loss of trust, context-aware applications should be intelligible, capable of explaining their behavior. We investigate providing intelligibility in context-aware applications and evaluate its usefulness to improve user understanding and trust in context-aware applications. Specifically, this thesis supports intelligibility in context-aware applications through the provision of explanations that answer different question types, such as: Why did it do X? Why did it not do Y? What if I did W, What will it do? How can I get the application to do Y? This thesis takes a three-pronged approach to investigating intelligibility by (i) eliciting the user requirements for intelligibility, to identify what explanation types end-users are interested in asking context-aware applications, (ii) supporting the development of intelligible context-aware applications with a software toolkit and the design of these applications with design and usability recommendations, and (iii) evaluating the impact of intelligibility on user understanding and trust under various situations and application reliability, and measuring how users use an interactive intelligible prototype. We show that users are willing to use well-designed intelligibility features, and this can improve user understanding and trust in the adaptive behavior of context-aware applications.

[1]  James Fogarty,et al.  Toolkit support for developing and deploying sensor-based statistical models of human situations , 2007, CHI.

[2]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[3]  Kazuya Murao,et al.  A Context-Aware System that Changes Sensor Combinations Considering Energy Consumption , 2008, Pervasive.

[4]  James A. Landay,et al.  UbiGreen: investigating a mobile tool for tracking and supporting green transportation habits , 2009, CHI.

[5]  Jadwiga Indulska,et al.  Developing context-aware pervasive computing applications: Models and approach , 2006, Pervasive Mob. Comput..

[6]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[7]  Carmen Lacave,et al.  A review of explanation methods for heuristic expert systems , 2004, The Knowledge Engineering Review.

[8]  Christopher A. Miller,et al.  Trust and etiquette in high-criticality automated systems , 2004, CACM.

[9]  Shwetak N. Patel,et al.  ElectriSense: single-point sensing using EMI for electrical event detection and classification in the home , 2010, UbiComp.

[10]  Aniket Kittur,et al.  Crowdsourcing user studies with Mechanical Turk , 2008, CHI.

[11]  Gregory D. Abowd,et al.  Distributed mediation of ambiguous context in aware environments , 2002, UIST '02.

[12]  Kris Luyten,et al.  I Bet You Look Good on the Wall: Making the Invisible Computer Visible , 2009, AmI.

[13]  Feng Zhao,et al.  Hapori: context-based local search for mobile phones using community behavioral modeling and similarity , 2010, UbiComp.

[14]  Allen E. Milewski,et al.  Providing presence cues to telephone users , 2000, CSCW '00.

[15]  Misha Pavel,et al.  A Statistical Reasoning System for Medication Prompting , 2007, UbiComp.

[16]  James A. Landay,et al.  Investigating statistical machine learning as a tool for software development , 2008, CHI.

[17]  Anders Kofod-Petersen,et al.  Explanations and Case-Based Reasoning in Ambient Intelligent Systems , 2007, CaCoA.

[18]  M. Chalmers,et al.  Seamful and Seamless Design in Ubiquitous Computing , 2003 .

[19]  Gwenn Englebienne,et al.  Accurate activity recognition in a home setting , 2008, UbiComp.

[20]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[21]  Desney S. Tan,et al.  Your noise is my command: sensing gestures using the body as an antenna , 2011, CHI.

[22]  J. K. Lowe,et al.  Some results and experiments in programming techniques for propositional logic , 1986, Comput. Oper. Res..

[23]  G Georgios Metaxas,et al.  End user programming of awareness systems : addressing cognitive and social challenges for interaction with aware environments , 2010 .

[24]  Karin Coninx,et al.  PervasiveCrystal: Asking and Answering Why and Why Not Questions about Pervasive Computing Applications , 2010, 2010 Sixth International Conference on Intelligent Environments.

[25]  Wanda J. Orlikowski,et al.  Using Technology and Constituting Structures: A Practice Lens for Studying Technology in Organizations , 2000, Theory in CSCW.

[26]  Edward H. Shortliffe,et al.  EMYCIN: A Knowledge Engineer’s Tool for Constructing Rule-Based Expert Systems , 2005 .

[27]  Masamichi Shimosaka,et al.  Hand shape classification with a wrist contour sensor: development of a prototype device , 2011, UbiComp '11.

[28]  Bob Hardian,et al.  Middleware support for transparency and user control in context-aware systems , 2006, MDS '06.

[29]  Daniel Roggen,et al.  Recognition of visual memory recall processes using eye movement analysis , 2011, UbiComp '11.

[30]  Bernt Schiele,et al.  Towards improving trust in context-aware systems by displaying system confidence , 2005, Mobile HCI.

[31]  Weng-Keen Wong,et al.  End-user feature labeling: a locally-weighted regression approach , 2011, IUI '11.

[32]  Antti Oulasvirta,et al.  Grounding the innovation of future technologies , 2005 .

[33]  Mark W. Newman,et al.  The infrastructure problem in HCI , 2010, CHI.

[34]  Anind K. Dey,et al.  Heuristic evaluation of ambient displays , 2003, CHI '03.

[35]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[36]  Peter L. Hammer,et al.  Boolean Functions - Theory, Algorithms, and Applications , 2011, Encyclopedia of mathematics and its applications.

[37]  J. Platt.  Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines , 1998 .

[38]  Scott E. Hudson,et al.  Responsiveness in instant messaging: predictive models supporting inter-personal communication , 2006, CHI.

[39]  David McSherry,et al.  Explanation in Recommender Systems , 2005, Artificial Intelligence Review.

[40]  Helen M. Edwards,et al.  Problem frames: analyzing and structuring software development problems , 2002, Softw. Test. Verification Reliab..

[41]  Bernt Schiele,et al.  Towards Personalized Mobile Interruptibility Estimation , 2006, LoCA.

[42]  W. Baggett,et al.  Question-driven Explanatory Reasoning , 1996 .

[43]  Mirco Musolesi,et al.  Sensing meets mobile social networks: the design, implementation and evaluation of the CenceMe application , 2008, SenSys '08.

[44]  Agnar Aamodt,et al.  Explanation in Case-Based Reasoning–Perspectives and Goals , 2005, Artificial Intelligence Review.

[45]  Peter Spieker,et al.  Natürlichsprachliche Erklärungen in technischen Expertensystemen , 1991 .

[46]  Franco Zambonelli,et al.  Detecting activities from body-worn accelerometers via instance-based algorithms , 2010, Pervasive Mob. Comput..

[47]  A. Graesser,et al.  Mechanisms that generate questions , 1992 .

[48]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[49]  John D. Lee,et al.  Trust in Automation: Designing for Appropriate Reliance , 2004, Hum. Factors.

[50]  Nava Tintarev,et al.  Explaining Recommendations , 2007, User Modeling.

[51]  Elizabeth D. Mynatt,et al.  Digital family portraits: supporting peace of mind for extended family members , 2001, CHI.

[52]  Brad A. Myers,et al.  Answering why and why not questions in user interfaces , 2006, CHI.

[53]  Jakob E. Bardram.  The Java Context Awareness Framework (JCAF) - A Service Infrastructure and Programming Framework for Context-Aware Applications , 2005, Pervasive.

[54]  Hilary Johnson,et al.  Explanation facilities and interactive systems , 1993, IUI '93.

[55]  Robert Tibshirani,et al.  Classification by Pairwise Coupling , 1997, NIPS.

[56]  Anind K. Dey,et al.  Embedded assessment of aging adults: A concept validation with stakeholders , 2010, 2010 4th International Conference on Pervasive Computing Technologies for Healthcare.

[57]  Martin Mozina,et al.  Nomograms for Visualization of Naive Bayesian Classifier , 2004, PKDD.

[58]  Gaetano Borriello,et al.  Reminding About Tagged Objects Using Passive RFIDs , 2004, UbiComp.

[59]  Li Chen,et al.  Trust building with explanation interfaces , 2006, IUI '06.

[60]  Anind K. Dey,et al.  From awareness to connectedness: the design and deployment of presence displays , 2006, CHI.

[61]  Giovanni Rimassa,et al.  Palpable Computing and the Role of Agent Technology , 2005, CEEMAS.

[62]  Stephen W. Smoliar,et al.  On making expert systems more like experts , 1987 .

[63]  Thomas Roth-Berghofer,et al.  Explanations and Case-Based Reasoning: Foundational Issues , 2004, ECCBR.

[64]  Todd Kulesza,et al.  Tell me more?: the effects of mental model soundness on personalizing an intelligent agent , 2012, CHI.

[65]  Agnar Aamodt,et al.  Knowledge-Intensive Case-Based Reasoning in CREEK , 2004, ECCBR.

[66]  Judy Kay,et al.  PersonisAD: Distributed, Active, Scrutable Model Framework for Context-Aware Services , 2007, Pervasive.

[67]  Oliver Brdiczka,et al.  Show me a good time: using content to provide activity awareness to collaborators with activityspotter , 2010, GROUP '10.

[68]  Agnar Aamodt,et al.  Explanatory Capabilities in the CREEK Knowledge-Intensive Case-Based Reasoner , 2008, SCAI.

[69]  Wendy Grace Lehnert,et al.  The Process of Question Answering , 2022 .

[70]  Joachim Diederich,et al.  The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks , 1998, IEEE Trans. Neural Networks.

[71]  John Zimmerman,et al.  Learning patterns of pick-ups and drop-offs to support busy family coordination , 2011, CHI.

[72]  Andrew T. Campbell,et al.  Cooperative Techniques Supporting Sensor-Based People-Centric Inferencing , 2009, Pervasive.

[73]  Edward H. Shortliffe,et al.  A rule-based computer program for advising physicians regarding antimicrobial therapy selection , 1974, ACM '74.

[74]  Kristina Höök,et al.  A glass box approach to adaptive hypermedia , 1996, User Modeling and User-Adapted Interaction.

[75]  Gregory D. Abowd,et al.  CybreMinder: A Context-Aware System for Supporting Reminders , 2000, HUC.

[76]  Tommy Burnette,et al.  Alice: lessons learned from building a 3D system for novices , 2000, CHI.

[77]  Kent Larson,et al.  Activity Recognition in the Home Using Simple and Ubiquitous Sensors , 2004, Pervasive.

[78]  Yoram Singer,et al.  Improved Boosting Algorithms Using Confidence-rated Predictions , 1998, COLT' 98.

[79]  Alexander De Luca,et al.  Visualization of uncertainty in context aware mobile applications , 2006, Mobile HCI.

[80]  Thomas G. Dietterich,et al.  Interacting meaningfully with machine learning systems: Three experiments , 2009, Int. J. Hum. Comput. Stud..

[81]  Dan R. Olsen,et al.  Evaluating user interface systems research , 2007, UIST.

[82]  Marius Mikalsen,et al.  Context: Representation and Reasoning. Representing and Reasoning about Context in a Mobile Environment , 2005, Rev. d'Intelligence Artif..

[83]  Stephanie Rosenthal,et al.  Using Decision-Theoretic Experience Sampling to Build Personalized Mobile Phone Interruption Models , 2011, Pervasive.

[84]  Teow-Hin Ngair,et al.  A New Algorithm for Incremental Prime Implicate Generation , 1993, IJCAI.

[85]  T. Damer,et al.  Attacking Faulty Reasoning: A Practical Guide to Fallacy-Free Arguments , 1980 .

[86]  Colin Ware,et al.  Information Visualization: Perception for Design , 2000 .

[87]  Koji Tsukada,et al.  ActiveBelt: Belt-Type Wearable Tactile Display for Directional Navigation , 2004, UbiComp.

[88]  Doina Bucur,et al.  Intelligible TinyOS Sensor Systems: Explanations for Embedded Software , 2011, CONTEXT.

[89]  Weng-Keen Wong,et al.  Fixing the program my computer learned: barriers for end users, challenges for the machine , 2009, IUI.

[90]  Christopher G. Atkeson,et al.  Simultaneous Tracking and Activity Recognition (STAR) Using Many Anonymous, Binary Sensors , 2005, Pervasive.

[91]  Simone Diniz Junqueira Barbosa,et al.  Semiotic engineering contributions for designing online help systems , 2001, SIGDOC '01.

[92]  Joe Tullio,et al.  How it works: a field study of non-technical users interacting with an intelligent system , 2007, CHI.

[93]  Mike Y. Chen,et al.  Tracking Free-Weight Exercises , 2007, UbiComp.

[94]  Joachim Diederich,et al.  Survey and critique of techniques for extracting rules from trained artificial neural networks , 1995, Knowl. Based Syst..

[95]  Brad A. Myers,et al.  Development and evaluation of a model of programming errors , 2003, IEEE Symposium on Human Centric Computing Languages and Environments, 2003. Proceedings. 2003.

[96]  Johnson Fong.  Intelligibility and user control of context-aware application behaviours , 2010, ICPS 2010.

[97]  Wei-Ying Ma,et al.  Understanding mobility based on GPS data , 2008, UbiComp.

[98]  Quanying Liu,et al.  A real-time EEG-based BCI system for attention recognition in ubiquitous environment , 2011, UAAII '11.

[99]  Joachim Diederich,et al.  Rule Extraction from Support Vector Machines , 2008, Studies in Computational Intelligence.

[100]  Judy Kay,et al.  IEMS - an approach that combines handcrafted rules with learnt instance based rules , 2006, Aust. J. Intell. Inf. Process. Syst..

[101]  Carmen Lacave,et al.  A review of explanation methods for Bayesian networks , 2002, The Knowledge Engineering Review.

[102]  Timothy Sohn,et al.  iCAP: Interactive Prototyping of Context-Aware Applications , 2006, Pervasive.

[103]  James H. Aylor,et al.  Computer for the 21st Century , 1999, Computer.

[104]  Bill N. Schilit,et al.  Context-aware computing applications , 1994, Workshop on Mobile Computing Systems and Applications.

[105]  Anind K. Dey,et al.  Support for context-aware intelligibility and control , 2009, CHI.

[106]  Anind K. Dey,et al.  Reflecting on pills and phone use: supporting awareness of functional abilities for older adults , 2011, CHI.

[107]  Andreas Zimmermann,et al.  Context-Awareness in User Modelling: Requirements Analysis for a Case-Based Reasoning Application , 2003, ICCBR.

[108]  Pat Langley,et al.  Induction of One-Level Decision Trees , 1992, ML.

[109]  Gaetano Borriello,et al.  A Practical Approach to Recognizing Physical Activities , 2006, Pervasive.

[110]  Anind K. Dey,et al.  Field Evaluation of an Intelligible Context-Aware Application , 2011 .

[111]  Boris E. R. de Ruyter,et al.  Daily Activities Diarist: Supporting Aging in Place with Semantically Enriched Narratives , 2007, INTERACT.

[112]  Mark W. Newman,et al.  Designing for serendipity: supporting end-user configuration of ubiquitous computing environments , 2002, DIS '02.

[113]  Izak Benbasat,et al.  Explanations From Intelligent Systems: Theoretical Foundations and Implications for Practice , 1999, MIS Q..

[114]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[115]  David F. Redmiles,et al.  Extracting usability information from user interface events , 2000, CSUR.

[116]  Gregory D. Abowd,et al.  A Conceptual Framework and a Toolkit for Supporting the Rapid Prototyping of Context-Aware Applications , 2001, Hum. Comput. Interact..

[117]  Tinghuai Ma,et al.  Context-aware implementation based on CBR for smart home , 2005, WiMob'2005), IEEE International Conference on Wireless And Mobile Computing, Networking And Communications, 2005..

[118]  Colin Potts,et al.  Design of Everyday Things , 1988 .

[119]  Deborah L. McGuinness,et al.  Toward establishing trust in adaptive agents , 2008, IUI '08.

[120]  Anind K. Dey,et al.  Location-Based Services for Mobile Telephony: a Study of Users' Privacy Concerns , 2003, INTERACT.

[121]  Paul Dourish,et al.  What we talk about when we talk about context , 2004, Personal and Ubiquitous Computing.

[122]  B. C. Smith,et al.  Organising User Interfaces Around Reflective Accounts , 1998 .

[123]  Anind K. Dey,et al.  Toolkit to support intelligibility in context-aware applications , 2010, UbiComp.

[124]  Wei Pan,et al.  SoundSense: scalable sound sensing for people-centric applications on mobile phones , 2009, MobiSys '09.

[125]  Brad A. Myers,et al.  Finding causes of program output with the Java Whyline , 2009, CHI.

[126]  Anind K. Dey,et al.  Is Context-Aware Computing Taking Control away from the User? Three Levels of Interactivity Examined , 2003, UbiComp.

[127]  Philip N. Johnson-Laird,et al.  The Spontaneous Use of Propositional Connectives , 1992 .

[128]  Alex Pentland,et al.  Social sensing for epidemiological behavior change , 2010, UbiComp.

[129]  Tsutomu Terada,et al.  Ubiquitous Chip: A Rule-Based I/O Control Device for Ubiquitous Computing , 2004, Pervasive.

[130]  John R. Anderson,et al.  Cognitive Tutors: Lessons Learned , 1995 .

[131]  John Riedl,et al.  Explaining collaborative filtering recommendations , 2000, CSCW '00.

[132]  Duane Szafron,et al.  Visual Explanation of Evidence with Additive Classifiers , 2006, AAAI.

[133]  John Seely Brown,et al.  The coming age of calm technolgy , 1997 .

[134]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[135]  A. Graesser,et al.  Anomalous Information Triggers Questions When Adults Solve Quantitative Problems and Comprehend Stories. , 1993 .

[136]  William R. Swartout,et al.  XPLAIN: A System for Creating and Explaining Expert Consulting Programs , 1983, Artif. Intell..

[137]  Srinivasan Keshav,et al.  An empirical approach to smartphone energy level prediction , 2011, UbiComp '11.

[138]  Gregory D. Abowd,et al.  Cyberguide: A mobile context‐aware tour guide , 1997, Wirel. Networks.

[139]  Anind K. Dey,et al.  Investigating intelligibility for uncertain context-aware applications , 2011, UbiComp '11.

[140]  Christopher G. Atkeson,et al.  Predicting human interruptibility with sensors , 2005, TCHI.

[141]  G. S. Tseitin.  On the Complexity of Derivation in Propositional Calculus , 1983 .

[142]  Gregory D. Abowd,et al.  Providing architectural support for building context-aware applications , 2000 .

[143]  Anind K. Dey,et al.  Design of an intelligible mobile context-aware application , 2011, Mobile HCI.

[144]  Jadwiga Indulska,et al.  A preference modelling approach to support intelligibility in pervasive applications , 2011, 2011 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops).

[145]  Wolfgang Effelsberg,et al.  A study on user acceptance of error visualization techniques , 2008, MobiQuitous.

[146]  Gerhard Tröster,et al.  Recognition of dietary activity events using on-body sensors , 2008, Artif. Intell. Medicine.

[147]  Padraig Cunningham,et al.  A Case-Based Explanation System for Black-Box Systems , 2005, Artificial Intelligence Review.

[148]  Xing Xie,et al.  Understanding transportation modes based on GPS data for web applications , 2010, TWEB.

[149]  Sadaoki Furui,et al.  Speaker recognition , 1997, Scholarpedia.

[150]  Anind K. Dey,et al.  Why and why not explanations improve the intelligibility of context-aware intelligent systems , 2009, CHI.

[151]  Edward H. Shortliffe,et al.  Production Rules as a Representation for a Knowledge-Based Consultation Program , 1977, Artif. Intell..

[152]  J. Gibson.  The Ecological Approach to Visual Perception , 1979 .

[153]  Pamela Jordan.  Basics of qualitative research: Grounded theory procedures and techniques , 1994 .

[154]  Virpi Roto,et al.  Examining mobile phone use in the wild with quasi-experimentation , 2004 .

[155]  Rich Caruana,et al.  Obtaining Calibrated Probabilities from Boosting , 2005, UAI.

[156]  W. Keith Edwards,et al.  Intelligibility and Accountability: Human Considerations in Context-Aware Systems , 2001, Hum. Comput. Interact..

[157]  Deborah L. McGuinness,et al.  A Categorization of Explanation Questions for Task Processing Systems , 2007, ExaCt.

[158]  Stephen S. Intille,et al.  Using wearable activity type detection to improve physical activity energy expenditure estimation , 2010, UbiComp.

[159]  Grady Booch,et al.  The Human Experience , 2012, IEEE Software.

[160]  Marko Robnik-Sikonja,et al.  Explaining Classifications For Individual Instances , 2008, IEEE Transactions on Knowledge and Data Engineering.

[161]  Eric C. Larson,et al.  Accurate and privacy preserving cough sensing using a low-cost microphone , 2011, UbiComp '11.

[162]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[163]  W. Baggett,et al.  Exploring information about concepts by asking questions , 1993 .

[164]  Saul Greenberg,et al.  Context as a Dynamic Construct , 2001, Hum. Comput. Interact..

[165]  Jadwiga Indulska,et al.  Exposing Contextual Information for Balancing Software Autonomy and User Control in Context-Aware Systems , 2008 .

[166]  Lin Sun,et al.  Physical Activity Monitoring with Mobile Phones , 2011, ICOST.

[167]  William G. Griswold,et al.  Mobility Detection Using Everyday GSM Traces , 2006, UbiComp.

[168]  Ron Kohavi,et al.  MineSet: An Integrated System for Data Mining , 1997, KDD.

[169]  Frank E. Ritter,et al.  Designs for explaining intelligent agents , 2009, Int. J. Hum. Comput. Stud..

[170]  Eyal de Lara,et al.  An Exploration of Location Error Estimation , 2007, UbiComp.

[171]  Regina A. Pomranky,et al.  The role of trust in automation reliance , 2003, Int. J. Hum. Comput. Stud..

[172]  Valtteri Niemi,et al.  Effects of Displaying Trust Information on Mobile Application Usage , 2010, ATC.

[173]  James R. Slagle,et al.  An explanation facility for today's expert systems , 1989, IEEE Expert.

[174]  Alex Groce,et al.  Mini-crowdsourcing end-user assessment of intelligent assistants: A cost-benefit study , 2011, 2011 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC).

[175]  Matthias Schonlau,et al.  Selection Bias in Web Surveys and the Use of Propensity Scores , 2006 .

[176]  Andre Michael Everett.  An empirical investigation of the effect of variations in expert system explanation presentation on users' acquisition of expertise and perceptions of the system , 1994 .

[177]  Eric C. Larson,et al.  HydroSense: infrastructure-mediated single-point sensing of whole-home water activity , 2009, UbiComp.

[178]  Jo Vermeulen,et al.  Improving intelligibility and control in Ubicomp , 2010, UbiComp '10 Adjunct.

[179]  Vanessa Evers,et al.  The effects of transparency on perceived and actual competence of a content-based recommender , 2008 .

[180]  Alex Groce,et al.  Where Are My Intelligent Assistant's Mistakes? A Systematic Testing Approach , 2011, IS-EUD.

[181]  Anind K. Dey,et al.  Assessing demand for intelligibility in context-aware applications , 2009, UbiComp.

[182]  Bernt Schiele,et al.  Evaluating the Effects of Displaying Uncertainty in Context-Aware Applications , 2004, UbiComp.

[183]  John T. Stasko,et al.  Mobile computing in the retail arena , 2003, CHI '03.

[184]  Tao Gu,et al.  A service-oriented middleware for building context-aware services , 2005, J. Netw. Comput. Appl..