Vio: a mixed-initiative approach to learning and automating procedural update tasks

ABSTRACT

Today many workers spend too much of their time translating their co-workers' requests into structures that information systems can understand. This paper presents the novel interaction design and evaluation of VIO, an agent that helps workers trans late request. VIO monitors requests and makes suggestions to speed up the translation. VIO allows users to quickly correct agent errors. These corrections are used to improve agent performance as it learns to automate work. Our evaluations demonstrate that this type of agent can significantly reduce task completion time, freeing workers from mundane tasks.

REFERENCES

• 1: Victoria Bellotti , Nicolas Ducheneaut , Mark Howard , Ian Smith, Taking email to task: the design and evaluation of a task management centered email tool, Proceedings of the SIGCHI conference on Human factors in computing systems, April 05-10, 2003, Ft. Lauderdale, Florida, USA [doi>10.1145/642611.642672]
• 2: Van Schaik, P., Jing, J. Five Psychometric Scales for Online Measurement of the Quality of Human-Computer Interaction in Web Sites. International Journal of Human-Computer Interaction 18, 3 (2005), 309--322.
• 3: Allen Cypher, Eager: programming repetitive tasks by demonstration, Watch what I do: programming by demonstration, MIT Press, Cambridge, MA, 1993
• 4: Nicolas Ducheneaut , Victoria Bellotti, E-mail as habitat: an exploration of embedded personal information management, interactions, v.8 n.5, p.30-38, Sept./Oct. 2001 [doi>10.1145/382899.383305]
• 5: Ferguson, G., Allen, J., Miller, B. TRAINS-95: Towards a Mixed-Initiative Planning Assistant. In Proc. of AIPS, AAAI Press (1996) 70--77.
• 6: James Fogarty , Scott E. Hudson , Christopher G. Atkeson , Daniel Avrahami , Jodi Forlizzi , Sara Kiesler , Johnny C. Lee , Jie Yang, Predicting human interruptibility with sensors, ACM Transactions on Computer-Human Interaction (TOCHI), v.12 n.1, p.119-146, March 2005 [doi>10.1145/1057237.1057243]
• 7: Mixed-Initiative Interaction, IEEE Intelligent Systems, v.14 n.5, p.14-23, September 1999 [doi>10.1109/5254.796083]
• 8: Eric Horvitz, Principles of mixed-initiative user interfaces, Proceedings of the SIGCHI conference on Human factors in computing systems: the CHI is the limit, p.159-166, May 15-20, 1999, Pittsburgh, Pennsylvania, United States [doi>10.1145/302979.303030]
• 9: John, B.E. Information processing and skilled behavior. In J. M. Carroll (Ed.) Toward a multidisciplinary science of human computer interaction Morgan Kaufman (2003), 55--101.
• 10: Bonnie E. John , Dario D. Salvucci, Multipurpose Prototypes for Assessing User Interfaces in Pervasive Computing Systems, IEEE Pervasive Computing, v.4 n.4, p.27-34, October 2005 [doi>10.1109/MPRV.2005.80]
• 11: Henry Lieberman, Autonomous interface agents, Proceedings of the SIGCHI conference on Human factors in computing systems, p.67-74, March 22-27, 1997, Atlanta, Georgia, United States [doi>10.1145/258549.258592]
• 12: Liebermann, H. Beating Some Common Sense into Interactive Applications. Seminar talk given at Carnegie Mellon's Human-Computer Interaction Institute. (February 23, 2005).
• 13: Andrea Lockerd , Huy Pham , Taly Sharon , Ted Selker, Mr.Web: an automated interactive webmaster, CHI '03 extended abstracts on Human factors in computing systems, April 05-10, 2003, Ft. Lauderdale, Florida, USA [doi>10.1145/765891.766007]
• 14: Thomas W. Malone , Kenneth R. Grant , Kum-Yew Lai , Ramana Rao , David Rosenblitt, Semistructured messages are surprisingly useful for computer-supported coordination, ACM Transactions on Information Systems (TOIS), v.5 n.2, p.115-131, April 1987 [doi>10.1145/27636.27637]
• 15: Frank Meng, A natural language interface for information retrieval from forms on the World Wide Web, Proceeding of the 20th international conference on Information Systems, p.540-545, December 12-15, 1999, Charlotte, North Carolina, United States
• 16: Remedy: http://www.bmc.com/remedy/
• 17: Ben Shneiderman , Pattie Maes, Direct manipulation vs. interface agents, interactions, v.4 n.6, p.42-61, Nov./Dec. 1997 [doi>10.1145/267505.267514]
• 18: Jeffrey Stylos , Brad A. Myers , Andrew Faulring, Citrine: providing intelligent copy-and-paste, Proceedings of the 17th annual ACM symposium on User interface software and technology, October 24-27, 2004, Santa Fe, NM, USA [doi>10.1145/1029632.1029665]
• 19: Tomasic, A., Simmons, I., Zimmerman, J., Experimental Evaluation of Processing Information Intent via Weak Labeling. Technical Report, Department of Computer Science, Carnegie Mellon University, pending.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)
          Subjects: Interaction styles (e.g., commands, menus, forms, direct manipulation)

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.7 Natural Language Processing
          Subjects: Language parsing and understanding

General Terms:
Design, Experimentation

Keywords:
agents, interaction design, mixed initiative