The Influence of Proactivity on Interactive Help Agents

The present study examined the effects of proactivity on users’ perception of an anthropomorphic user interface agent. The focus was on assessing subjective differences in agent perception between proactive and reactive conditions. Participants of the study were assisted by an interactive agent during seven tasks in a simulation controlling a nuclear power plant. In the reactive condition users had to activate the agent manually in case they needed help. In the proactive condition the agent offered help at a well defined time in the interaction process. Namely when users had confirmed that they were done reading the current task description. The complexity of the simulation ensured that solving the tasks without consulting the agent was virtually impossible. While both conditions performed similarly on objective performance criteria, the reactive agent was perceived more positively than the proactive agent. Especially the reactive agent was rated to be less distracting and less dominant.

[1]  B. Karsh,et al.  Occupational stress in human computer interaction. , 1999, Industrial health.

[2]  Ben Shneiderman,et al.  Determining Causes and Severity of End-User Frustration , 2004, Int. J. Hum. Comput. Interact..

[3]  Jacob Cohen Statistical Power Analysis for the Behavioral Sciences , 1969, The SAGE Encyclopedia of Research Design.

[4]  Jingtao Yao,et al.  On Web-based Support Systems , 2010, IICAI.

[5]  John T. Stasko,et al.  An empirical study of the effect of agent competence on user performance and perception , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[6]  Shahbaz Khan,et al.  Helplets: A Common Sense-Based Collaborative Help Collection and Retrieval Architecture for Web-Enabled Systems ∗ , 2010 .

[7]  Akrivi Katifori,et al.  From the web of data to a world of action , 2010, J. Web Semant..

[8]  Yanghee Kim,et al.  Pedagogical Agents as Learning Companions: The Role of Agent Competency and Type of Interaction , 2006 .

[9]  Wolfgang Minker,et al.  A collaborative web-based help-system , 2012, WIMS '12.

[10]  Sriram Subramanian,et al.  Talking about tactile experiences , 2013, CHI.

[11]  Ben Shneiderman,et al.  Workplace user frustration with computers: an exploratory investigation of the causes and severity , 2006, Behav. Inf. Technol..

[12]  Michael Kipp,et al.  ANVIL - a generic annotation tool for multimodal dialogue , 2001, INTERSPEECH.

[13]  Michael Burmester,et al.  AttrakDiff: Ein Fragebogen zur Messung wahrgenommener hedonischer und pragmatischer Qualität , 2003, MuC.

[14]  Byron Reeves,et al.  The effects of animated characters on anxiety, task performance, and evaluations of user interfaces , 2000, CHI.

[15]  H. Levene Robust tests for equality of variances , 1961 .

[16]  C. Nass,et al.  Machines and Mindlessness , 2000 .

[17]  John T. Stasko,et al.  Be Quiet? Evaluating Proactive and Reactive User Interface Assistants , 2003, INTERACT.

[18]  Welch Bl THE GENERALIZATION OF ‘STUDENT'S’ PROBLEM WHEN SEVERAL DIFFERENT POPULATION VARLANCES ARE INVOLVED , 1947 .

[19]  Wolfgang Minker,et al.  An Avatar-Based Help System for Web-Portals , 2011, HCI.

[20]  Ben Shneiderman,et al.  Severity and impact of computer user frustration: A comparison of student and workplace users , 2006, Interact. Comput..