Time and Location:

Winter 2007

Tuesday,Thursday, 12:00-1:20, Usually in CSE 503

Course Description:

Systems based on statistical learning and pseudo-intelligence introduce new opportunities and challenges in the design, development, and evaluation of human-computer interfaces. We will study work from the HCI community that addresses this intersection of HCI and intelligent systems.

Topics will include innovative applications of statistical learning in interfaces, synergistic correspondences between the needs of an end-user and the needs of a machine learning algorithm, especially well-designed studies of statistical models of human situations, and interface-based approaches to addressing breakdowns and limitations in a learning system.

This course is explicitly not an introduction to machine learning and is not intended to require extensive knowledge of machine learning. While we will occasionally review basic terminology, the HCI issues examined in this course are important independent of a particular algorithm or system.

Workload:

This course will be based on research readings and a group term project.

Each meeting's discussion will be led by either a guest or by a volunteer from the class. The number of times it is necessary for each student to volunteer will depend on enrollment. These discussions should be informal and enjoyable, as it is important that everybody feel comfortable commenting and offering their insight. The participation component of grading in this course will be based both on apparent preparation to lead discussion and on active participation in discussion throughout the course.

Grading will roughly correspond to 60% project, 20% participation, and 20% reading reports.

Reading Reports:

Because I know you have many demands for your time, I will assign only one reading for most classes. But I will expect you to have read and thought carefully about that reading. To help you out, I will require short written reading reports. Reading reports should be between 300 and 500 words, posted in this forum:

https://catalysttools.washington.edu/gopost/board/jaf1978/128

Reports should be posted by the midnight before each class meeting, ensuring that the day's discussion coordinator has ample time to review them. Feel free to read and comment on other people's reports after you have posted your own.

In writing these reports, note that it is generally easy to find something to criticize in any piece of research, but that focusing on this is typically not productive. You will generally find it more intellectually worthwhile to focus on what aspects of a piece of work are particularly well done, what new ideas are prompted by a piece of work, or what you might have done differently if you conducted the research. This will also lead to much more valuable discussions.

Potential topics for consideration in your report are:

What idea or innovation enabled this research?
Is there more to be had from that idea or innovation?
What new questions or research agendas are suggested by this research?
What would you have done differently with approximately the same resources available to the original authors?
What would you have done differently with twice or half the resources available to the original authors?
How might this research have informed some other research you've seen?

These are only some suggestions for topics in your report. The important part is that I can see an intellectual effort in your report, not a simple summary.

Term Projects:

Term projects will be conducted in groups of two to three students. Projects should be research-oriented, related to human-computer interaction (to the degree that it might be appropriate to publish the results of a project at a conference like CHI, UIST, or UbiComp), and have some relation to an intelligent system (though I will be very open-minded with this last requirement).

Given the limited time available, it is important to get a quick start on your projects. I intend to be highly available for discussion of potential projects within the first two weeks of the course. A finalized proposal will be due at the beginning of the fourth class. You will also briefly present your finalized proposals.

The primary project deliverable will be a paper in CHI Archival Format. Papers may not exceed 10 pages, but the length of your paper should be commensurate with the contribution of your project. If the choice is between a solid 6 page paper and a 10 page paper that contains 4 pages of fluff, I would much rather you turn in the solid 6 page paper. It is absolutely critical that you practice distilling your ideas and contributions into a research paper format, but I will also be willing to acknowledge software systems or other such substantive project results.

There will also be a mid-quarter status update and a final presentation / poster session.

Calendar:

Date	Location	Reading	Presenter	Due
Jan 4	CSE 403	Stylos, J., Myers, B.A., and Faulring, A. (2004). Citrine: Providing Intelligent Copy-and-Paste. Proceedings of the ACM Symposium on User Interface Software and Technology (UIST 2004), pp. 185-188.	James Fogarty	Form Groups and Discuss Projects
Jan 9	CSE 503	Little, G. and Miller, R.C. (2006). Translating Keyword Commands into Executable Code. Proceedings of the ACM Symposium on User Interface Software and Technology (UIST 2006), pp. 135-144.	Michael Toomim	Reading Report
Jan 11	CSE 503	Agrawala, M. and Stolte, C. (2001). Rendering Effective Route Maps: Improving Usability Through Generalization. Proceedings of the ACM Conference on Computer Graphics and Interactive Techniques (SIGGRAPH 2001), pp. 909-918.	Jeffrey Bigham	Reading Report
Jan 16	CSE 503	Project Proposal Presentations Avrahami, D. and Hudson, S.E. (2006). QnA: Augmenting an Instant Messaging Client to Balance User Responsiveness and Performance. Proceedings of the ACM Conference on Computer Supported Cooperative Work (CSCW 2004), pp. 515-518.	James Fogarty	Project Proposal Reading Report
Jan 18	CSE 503	Mankoff, J., Hudson, S.E., and Abowd, G.D. (2000). Interaction Techniques for Ambiguity Resolution in Recognition-Based Interfaces. Proceedings of the ACM Symposium on User Interface Software and Technology (UIST 2000), pp. 11-20.	Kayur Patel	Reading Report
Jan 23	CSE 503	Horvitz, E. (1999). Principles of Mixed-Initiative Interfaces. Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 1999), pp. 159-166.	Eric Horvitz, MSR	Reading Report
Jan 25	CSE 503	Shilman, M., Tan, D.S., and Simard, P. (2006). CueTIP: A Mixed-Initiative Interface for Correcting Handwriting Errors. Proceedings of the ACM Symposium on User Interface Software and Technology (UIST 2006), pp. 323-332.	Adrienne Andrew	Reading Report
Jan 30	CSE 403	Kristjannson, T., Culotta, A., Viola, P., and McCallum, A. (2004). Interactive Information Extraction with Constrained Conditional Random Fields. Proceedings of the National Conference on Artificial Intelligence (AAAI 2004), pp. 412-418.	Desney Tan, MSR	Reading Report
Feb 1	CSE 503	Shneiderman, B. and Maes, P. (1997). Direct Manipulation vs. Interface Agents. Interactions, 4(6), pp. 42-61.	Desney Tan, MSR	Reading Report
Feb 6	CSE 503	Bunt, A., Conati, C., and McGrenere, J. (2007). Supporting Interface Customization using a Mixed-Initiatve Approach. Proceedings of the International Conference on Intelligent User Interfaces (IUI 2007), pp. 92-101.	Jon Froehlich	Reading Report
Feb 8	CSE 503	Fails, J. and Olsen, D. (2003). A Design Tool for Camera-Based Interaction. Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2003), pp. 449-456.	Susumu Harada	Reading Report
Feb 13	CSE 403	Xie, X., Liu, H., Goumaz, S., and Ma, W.Y. (2005). Learning User Interest for Image Browsing on Small-Form-Factor Devices. Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2005), pp. 671-680.	Christopher Frederick	Project Status Reading Report
Feb 15	CSE 503	Rosenholtz, R., Li, Y., Mansfield, J. and Jin, Z. (2005). Feature Congestion: A Measure of Display Clutter. Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2005), pp. 761-770.	Katherine Everitt	Reading Report
Feb 20	CSE 503	Class Presentations of Interesting Method Papers	Ludvig Suneson	Reading Report
Feb 22	CSE 503	Class Presentations of Interesting Method Papers
Feb 27	CSE 503	Fogarty, J., Ko, A.J., Aung, H.H., Golden, E., Tang, K.P. and Hudson, S.E. (2005). Examining Task Engagement in Sensor-Based Statistical Models of Human Interruptibility. Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2005), pp. 331-340.	Saleema Amershi	Reading Report Optional
March 1	CSE 503	Ho, J. and Intille, S. S. (2005). Using Context-Aware Computing to Reduce the Perceived Burden of Interruptions from Mobile Devices. Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2005), pp. 909-918.	Scott Saponas	Reading Report
March 6	CSE 503	Bellotti, V., Back, M., Edwards, K.E., Grinter, R.E., Henderson, A. and Lopes, C. (2002). Making Sense of Sensing Systems: Five Questions for Designers and Researchers. Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2002), pp. 415-422.	Ryan Wolfe	Reading Report
March 8	CSE 503	Project Presentations
March 15	CSE 503			Project Paper