Do Make me Think!: How CUIs Can Support Cognitive Processes

Traditionally, a key concern of HCI has been to design interfaces that should not make the user think. While this is - and will continue to be - desirable for most systems, there are also situations in which a system that prompts and questions the user may be more appropriate. In educational systems for instance, tasks are often intentionally made more challenging to enable "deeper" thinking and more thorough learning. Although conversational interfaces are still relatively limited in their capabilities, they seem very promising for contexts where questioning is needed, such as learning, analytics or sensemaking as well as safety-critical systems. Overly simple interactions - such as when the user can just tap or drag and drop - may not be beneficial in this context or may even be risky. In this position paper, we discuss previous work as well as opportunities where questioning users through conversation can be beneficial, based on insights from our own research.

[1]  Melanie Tory,et al.  How Information Visualization Novices Construct Visualizations , 2010, IEEE Trans. Vis. Comput. Graph..

[2]  Vidya Setlur,et al.  Applying Pragmatics Principles for Interaction with Visual Analytics , 2018, IEEE Transactions on Visualization and Computer Graphics.

[3]  John W. Tukey,et al.  We Need Both Exploratory and Confirmatory , 1980 .

[4]  Jignesh M. Patel,et al.  Ava: From Data to Insights Through Conversations , 2017, CIDR.

[5]  Stavros N. Demetriadis,et al.  Conversational Agents Improve Peer Learning through Building on Prior Knowledge , 2017, J. Educ. Technol. Soc..

[6]  Jan Marco Leimeister,et al.  Alexa, Can You Help Us Solve This Problem?: How Conversations With Smart Personal Assistant Tutors Increase Task Group Outcomes , 2019, CHI Extended Abstracts.

[7]  Michael J. Hannafin,et al.  Scaffolding problem solving in technology-enhanced learning environments (TELEs): Bridging research and theory with practice , 2011, Comput. Educ..

[8]  Annemarie S. Palincsar,et al.  Guiding students towards sensemaking: teacher questions focused on integrating scientific practices with science content , 2017 .

[9]  Sebastian Hobert,et al.  Sara, the Lecturer: Improving Learning in Online Education with a Scaffolding-Based Conversational Agent , 2020, CHI.

[10]  Brian D. Fisher,et al.  Pair Analytics: Capturing Reasoning Processes in Collaborative Visual Analytics , 2011, 2011 44th Hawaii International Conference on System Sciences.

[11]  Donggil Song,et al.  Interacting with a conversational agent system for educational purposes in online courses , 2017, 2017 10th International Conference on Human System Interactions (HSI).

[12]  Vidya Setlur,et al.  Eviza: A Natural Language Interface for Visual Analysis , 2016, UIST.

[13]  K. Kowalski The value of asking questions. , 2007, Journal of continuing education in nursing.

[14]  Brian J. Reiser,et al.  Scaffolding Complex Learning: The Mechanisms of Structuring and Problematizing Student Work , 2004, The Journal of the Learning Sciences.

[15]  Steve Krug Don't Make Me Think: A Common Sense Approach to the Web (2nd Edition) , 2005 .

[16]  Michael S. Bernstein,et al.  Iris: A Conversational Agent for Complex Tasks , 2017, CHI.