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

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.

[1]  K. R. Grant,et al.  Semistructured messages are surprisingly useful for computer-supported coordination , 1987, TOIS.

[2]  Allen Cypher,et al.  Eager: programming repetitive tasks by demonstration , 1993 .

[3]  James F. Allen,et al.  TRAINS-95: Towards a Mixed-Initiative Planning Assistant , 1996, AIPS.

[4]  Ben Shneiderman,et al.  Direct manipulation vs. interface agents , 1997, INTR.

[5]  Henry Lieberman,et al.  Autonomous interface agents , 1997, CHI.

[6]  Eric Horvitz,et al.  Principles of mixed-initiative user interfaces , 1999, CHI '99.

[7]  Curry Guinn,et al.  Mixed-initiative interaction , 1999 .

[8]  Marti A. Hearst Mixed-initiative interaction , 1999 .

[9]  Frank Meng A natural language interface for information retrieval from forms on the World Wide Web , 1999, ICIS.

[10]  Victoria Bellotti,et al.  E-mail as habitat: an exploration of embedded personal information management , 2001, INTR.

[11]  B. John Information Processing and Skilled Behavior , 2003 .

[12]  Bonnie E. John,et al.  CHAPTER 4 – Information Processing and Skilled Behavior , 2003 .

[13]  Andrea Lockerd Thomaz,et al.  Mr.Web: an automated interactive webmaster , 2003, CHI Extended Abstracts.

[14]  Ian Smith,et al.  Taking email to task: the design and evaluation of a task management centered email tool , 2003, CHI '03.

[15]  Barbara Barry,et al.  Beating Some Common Sense into Interactive Applications , 2003 .

[16]  Brad A. Myers,et al.  Citrine: providing intelligent copy-and-paste , 2004, UIST '04.

[17]  Paul van Schaik,et al.  Five Psychometric Scales for Online Measurement of the Quality of Human-Computer Interaction in Web Sites , 2005, Int. J. Hum. Comput. Interact..

[18]  Bonnie E. John,et al.  Multipurpose prototypes for assessing user interfaces in pervasive computing systems , 2005, IEEE Pervasive Computing.

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

[20]  John Zimmerman,et al.  Learning information intent via observation , 2007, WWW '07.