Q. Vera Liao
Werner Geyer
N. Sadat Shami
ABSTRACT
Personal agent software is now in daily use in personal devices and in some organizational settings. While many advocate an agent sociality design paradigm that incorporates human-like features and social dialogues, it is unclear whether this is a good match for professionals who seek productivity instead of leisurely use. We conducted a 17-day field study of a prototype of a personal AI agent that helps employees find work-related information. Using log data, surveys, and interviews, we found individual differences in the preference for humanized social interactions (social-agent orientation), which led to different user needs and requirements for agent design. We also explored the effect of agent proactive interactions and found that they carried the risk of interruption, especially for users who were generally averse to interruptions at work. Further, we found that user differences in social-agent orientation and aversion to agent proactive interactions can be inferred from behavioral signals. Our results inform research into social agent design, proactive agent interaction, and personalization of AI agents.
- Apple's Siri wrong 38 percent of the time in test. http://www.cnet.com/news/apples-siri-wrong-38percent-of-the-time-in-test/Google Scholar
- Bailey, B. P., & Konstan, J. A. On the need for attention-aware systems: Measuring effects of interruption on task performance, error rate, and affective state. Computers in human behavior 22, 4(2006), 685--708.Google Scholar
- Berry, P., Peintner, B., Conley, K., Gervasio, M., Uribe, T., and Yorke-Smith, N. Deploying a personalized time management agent. In Proc. AAMAS 2006, ACM Press (2006), 1564--1571). Google ScholarDigital Library
- Bickmore, T., and Cassell, J. Relational agents: a model and implementation of building user trust. In Proc. CHI 2001, ACM Press (2001), 396--403. Google ScholarDigital Library
- Bickmore, T., Mauer, D., Crespo, F., and Brown, T. Persuasion, task interruption and health regimen adherence. In Proc. Persuasive Technology, 1--11. Google ScholarDigital Library
- Bickmore, T. W., Pfeifer, L. M., and Jack, B. W. Taking the time to care: empowering low health literacy hospital patients with virtual nurse agents. In Proc. CHI 2009, ACM Press (2009), 1265--1274. Google ScholarDigital Library
- Bickmore, T. W., and Picard, R. W. Establishing and maintaining long-term human-computer relationships. ACM Transactions on Computer-Human Interaction (TOCHI) 12, 2 (2005), 293--327. Google ScholarDigital Library
- Brave, S., Nass, C., and Hutchinson, K. Computers that care: investigating the effects of orientation of emotion exhibited by an embodied computer agent. International Journal of Human-Computer Studies 62, 2 (2005), 161--178. Google ScholarDigital Library
- Cassell, Justine. Embodied conversational agents. MIT press, 2000.Google ScholarCross Ref
- Cassell, J., & Bickmore, T. (2003). Negotiated collusion: Modeling social language and its relationship effects in intelligent agents. User Modeling and User-Adapted Interaction, 13(1--2), 89--132. Google ScholarDigital Library
- Cassell, J., and Thorisson, K. R. The power of a nod and a glance: Envelope vs. emotional feedback in animated conversational agents. Applied Artificial Intelligence 13, 4--5(1999), 519--538.Google ScholarCross Ref
- Chi, E. H. Blurring of the Boundary Between Interactive Search and Recommendation. In Proc. IUI 2015, ACM Press (2015), 2--2. Google ScholarDigital Library
- Clark, H. H., and Brennan, S. E. Grounding in communication. Perspectives on socially shared cognition, 13(1991), 127--149.Google Scholar
- Cramer, H., Evers, V., van Slooten, T., Ghijsen, M., & Wielinga, B. Trying too hard: effects of mobile agents'(Inappropriate) social expressiveness on trust, affect and compliance. In Proc. CHI 2010, ACM Press (2010), 1471--1474. Google ScholarDigital Library
- Czerwinski, M., Horvitz, E., & Wilhite, S. A diary study of task switching and interruptions. In Proc. CHI 2004, ACM Press (2004), 175--182. Google ScholarDigital Library
- Dautenhahn, K. Robots we like to live with?!-a developmental perspective on a personalized, life-long robot companion. In Robot and Human Interactive Communication 2004. 17--22.Google Scholar
- Dryer, D. C. Getting personal with computers: how to design personalities for agents. Applied Artificial Intelligence 13, 3 (1999), 273--295.Google ScholarCross Ref
- Faulring, A., Myers, B., Mohnkern, K., Schmerl, B., Steinfeld, A., Zimmerman, J. and Siewiorek, D. Agentassisted task management that reduces email overload. In Proc. IUI 2010, ACM Press (2010),61--70. Google ScholarDigital Library
- Friedman, B., Kahn Jr, P. H., and Hagman, J. Hardware companions': What online AIBO discussion forums reveal about the human-robotic relationship. In Proc. 2003, ACM Press (2003), 273--280). Google ScholarDigital Library
- Gil, Y., and Ratnakar, V. Towards intelligent assistance for to-do lists. In Proc. IUI 2008, ACM Press (2008), 329--332. Google ScholarDigital Library
- Gockley, R., Bruce, A., Forlizzi, J., Michalowski, M., Mundell, A., Rosenthal, S. andWang, J. Designing robots for long-term social interaction. In Intelligent Robots and Systems 2005, 1338--1343.Google Scholar
- Goetz, J., Kiesler, S., and Powers, A. Matching robot appearance and behavior to tasks to improve humanrobot cooperation. In Robot and Human Interactive Communication 2003, 55--60.Google Scholar
- Ho, J., and Intille, S. S. Using context-aware computing to reduce the perceived burden of interruptions from mobile devices. In Proc. CHI 2005. ACM Press (2005), 909--918. Google ScholarDigital Library
- Kim, Y., Baylor, A. L., & PALS Group. Pedagogical agents as learning companions: The role of agent competency and type of interaction. Educational Technology Research and Development 54,3 (2006), 223--243.Google Scholar
- Kopp, S., Gesellensetter, L., Krämer, N. C., and Wachsmuth, I. A conversational agent as museum guide-design and evaluation of a real-world application. In Intelligent Virtual Agents, (2005), 329343. Google ScholarDigital Library
- Kshirsagar, S. A multilayer personality model. In Proceedings of the 2nd international symposium on Smart graphics 2002, 107--115. Google ScholarDigital Library
- Kuno, Y., Sadazuka, K., Kawashima, M., Yamazaki, K., Yamazaki, A., and Kuzuoka, H. Museum guide robot based on sociological interaction analysis. In Pro. CHI 2007, ACM Press (2007), 1191--1194. Google ScholarDigital Library
- Lee, M. K., Kiesler, S., and Forlizzi, J. Receptionist or information kiosk: how do people talk with a robot?. In Proc. CSCW 2010, ACM Press (2010), 31--40. Google ScholarDigital Library
- Lee, M. K., Kiesler, S., Forlizzi, J., and Rybski, P. Ripple effects of an embedded social agent: a field study of a social robot in the workplace. In Proc CHI 2012, ACM Press (2012), 695--704. Google ScholarDigital Library
- Lee, N., Shin, H., & Sundar, S. S. Utilitarian vs. hedonic robots: role of parasocial tendency and anthropomorphism in shaping user attitudes. In Proc HRI 2011, ACM Press (2011), 183--184. Google ScholarDigital Library
- Maes, P. Agents that reduce work and information overload.Communications of the ACM 37,7(1994), 3040. Google ScholarDigital Library
- Morris, M. R., & Horvitz, E. SearchTogether: an interface for collaborative web search. In Proc. UIST 2007, ACM Press (2007), 3--12. Google ScholarDigital Library
- Nass, C., and Lee, K. M. Does computer-generated speech manifest personality? An experimental test of similarity-attraction. In Proc CHI 2012, ACM Press (2012),329--336. Google ScholarDigital Library
- Nass, C., Steuer, J., and Tauber, E. R. Computers are social actors. In Proc. CHI 1994. ACM Press (1994), 72--78. Google ScholarDigital Library
- Norman, D. A. (2002). The Design of Everyday Things. Google ScholarDigital Library
- Novielli, N., de Rosis, F., & Mazzotta, I. (2010). User attitude towards an embodied conversational agent: Effects of the interaction mode. Journal of Pragmatics, 42(9), 2385--2397.Google Scholar
- Nowak, K. L. and Biocca, F. The effect of the agency and anthropomorphism on users' sense of telepresence, copresence, and social presence in virtual environments. Presence 12, 5(2003), 481--494. Google ScholarDigital Library
- O'Conaill, B., & Frohlich, D. Timespace in the workplace: Dealing with interruptions. In Proc. CHI 1995, ACM Press (1995), 262--263. Google ScholarDigital Library
- Ogan, A., Finkelstein, S., Mayfield, E., D'Adamo, C., Matsuda, N., and Cassell, J. Oh dear stacy!: social interaction, elaboration, and learning with teachable agents. In Proc. CHI 2012, ACM Press (2012), 39--48. Google ScholarDigital Library
- Picard, R. W., and Picard, R. (1997). Affective computing (Vol. 252). Cambridge: MIT press. Google ScholarDigital Library
- Prendinger, H., and Ishizuka, M. Social role awareness in animated agents. In Proceedings of the fifth international conference on Autonomous agents. ACM Press (2001), 270--277. Google ScholarDigital Library
- Salem, M., Lakatos, G., Amirabdollahian, F. and Dautenhahn, K. Would You Trust a (Faulty) Robot?: Effects of Error, Task Type and Personality on HumanRobot Cooperation and Trust. In Proc. HRI 2015, ACM Press (2015), 141--148. Google ScholarDigital Library
- Satake, S., Kanda, T., Glas, D. F., Imai, M., Ishiguro, H., and Hagita, N. How to approach humans-strategies for social robots to initiate interaction. In Proc. HRI 2009, ACM Press (2009), 109--116). Google ScholarDigital Library
- Strauss, A., & Corbin, J. Grounded theory methodology. Handbook of qualitative research, (1997), 273--285.Google Scholar
- Tapus, A., Ţăpuş, C., and Matarić, M. J. User-robot personality matching and assistive robot behavior adaptation for post-stroke rehabilitation therapy. Intelligent Service Robotics1, 2(2008), 169--183.Google ScholarCross Ref
- Thompson, C. A., Goker, M. H., and Langley, P. A personalized system for conversational recommendations. Journal of Artificial Intelligence Research, (2004), 393--428. Google ScholarDigital Library
- Weizenbaum, J. ELIZA--a computer program for the study of natural language communication between man and machine. Communications of the ACM 9, 1(1966), 36--45. Google ScholarDigital Library
- Xiao, J., Stasko, J., and Catrambone, R. An empirical study of the effect of agent competence on user performance and perception. In Proc. AAMAS. IEEE Computer Society (2004),178--185. Google ScholarDigital Library
- Xiao, J., Stasko, J., and Catrambone, R. The role of choice and customization on users' interaction with embodied conversational agents: effects on perception and performance. In Proc. CHI 2007, ACM Press (2007) 1293--1302. Google ScholarDigital Library
- Yan, H., & Selker, T. Context-aware office assistant. In Proc 2000, ACM Press (2000), 276--279). Google ScholarDigital Library
- Yee, N., Bailenson, J. N., and Rickertsen, K.. A metaanalysis of the impact of the inclusion and realism of human-like faces on user experiences in interfaces. In Proc. 2007, ACM Press (2007), 1--10. Google ScholarDigital Library
- Yorke-Smith, N., Saadati, S., Myers, K. L., and Morley, D. N. Like an intuitive and courteous butler: a proactive personal agent for task management. In Proc AAMAS 2009. 337--344. Google ScholarDigital Library
- Watson Dialog Service. http://www.ibm.com/smarterplanet/us/en/ibmwatson/de velopercloud/dialog.htmlGoogle Scholar
Index Terms
- What Can You Do?: Studying Social-Agent Orientation and Agent Proactive Interactions with an Agent for Employees
Recommendations
PVA: A Self-Adaptive Personal View Agent
In this paper, we present PVA, an adaptive personal view information agent system for tracking, learning and managing user interests in Internet documents. PVA consists of three parts: a proxy, personal view constructor, and personal view maintainer. ...
Forming Coalitions in Self-interested Multi-agent Environments Through the Promotion of Fair and Cooperative Behaviour
Multi-Agent SystemsAbstractThe issue of collaboration amongst agents in a multi-agent system (MAS) represents a challenging research problem. In this paper we focus on a form of cooperation known as coalition formation. The problem we consider is how to facilitate the ...
The RETSINA MAS Infrastructure
RETSINA is an implemented Multi-Agent System infrastructure that has been developed for several years and applied in many domains ranging from financial portfolio management to logistic planning. In this paper, we distill from our experience in ...
Comments