[Research] Auton Lab meeting on Tuesday April 28th

[Artur Dubrawski]

Dear Autonians,

On Tuesday we will have a guest speaker: Xinlong Bao.
Xinlong is a soon-to-graduate Ph.D. student in Tom Dietterich's
team at Oregon State University.

Please see below the abstract of the talk and the short bio of
the speaker.

We will meet at the usual place and time.

Besides giving his talk at our noon meeting, Xinlong will
be available for one-on-one meetings between approx. 9am and 3pm.
Please contact Karen Widmaier to get your name on the schedule.

*Title of the talk*:
TaskTracer: Intelligent Assistants for Supporting Multitasking Knowledge
Workers

*Abstract*:
Knowledge workers are multi-taskers. Their work lives can be divided
into multiple on-going projects or activities (we call them "tasks"),
and their time at the desktop interleaves work on these
tasks. However, existing desktop user interfaces do not have any
notion of coherent tasks. The TaskTracer system seeks to support these
workers by organizing the files, folders, contact information,
calendar appointments, and web sites (collectively known as
"resources") according to the tasks that they support. To use
TaskTracer, the user defines a hierarchy of tasks and declares to
TaskTracer what current task he/she is working on at each point in
time. TaskTracer instruments Microsoft Windows and Office to gather
data on the resources that are accessed by the user and associates
them with the currently-declared task. It then provides tasks-related
assistance through (a) the TaskExplorer (which makes it easy for the
user to return to previously-accessed resources), (b) the
FolderPredictor (which predicts the relevant folder for Open and
SaveAs actions).
Over the past year, we conducted a user study at Intel to evaluate the
hypotheses underlying the design of TaskTracer and to evaluate
alternative designs for the Folder Predictor.  This talk to describe
these hypotheses and present the results of the study.  The results
show strong support for task-oriented user interfaces.

*Short bio*:
Xinlong Bao is a Ph.D. candidate in Computer science at Oregon State
University. He received his Master's and Bachelor's degree from the
University of Science and Technology of China in 2004 and 2001,
respectively. During the summer of 2008, he was an intern at IBM Research.
 His primary research interests are in the field of machine learning,
where he focuses on intelligent predictions based on user behaviors,
recommender systems, and integrating learning and reasoning.