Hello folks,
We will have another candidate for the data vis position, *Chris
Collins*, visiting
on *Monday Feb 26*. Events of interest include:
- His talk is at *11am, at GB303*
- The student round table will be at *4PM @ BA 5187*
Abstract of the talk and bio follow below, for your convenience.
Also, please note that the candidate has asked to keep his application
*confidential*. As such, please* do not circulate this note or advertise
this event* to anyone outside UofT. Thanks!
Hope to see you all on Monday,
Nicole
------------------
*Title*: Mixed-Initiative Visual Analytics: Model-driven Views and Analytic
Guidance
*Presented By*: Christopher Collins, University of Ontario Institute of
Technology
*Abstract*: The classic information visualization design pattern of
“overview first, zoom and filter, details on demand” is no longer
sufficient. As datasets have grown (and small displays have become more
prevalent), simple overviews tend to be either too high-level to be useful,
or too cluttered to reveal anything interesting. The task of exploring and
sifting through the data is left only to the analyst in this traditional
model. It doesn't have to be this way: well-designed computational models
of various sorts can augment the analysis process by highlighting patterns
and drawing attention to regions of potential interest. I seek to
facilitate a closely coupled interaction between people and underlying
computational models, mediated by visualizations which include algorithmic
transparency as to what guidance is being provided or what data is being
hidden.
In this talk I will discuss several recent research projects which use
various types of models to improve the human-computer visual analytic
complex. Linguistic, interaction, information, and perception models can
provide data-driven visualization views and create suggestions of starting
points for analysis, just-in-time data curation, and guidance for
next steps. I will discuss my vision for the future of mixed-initiative
analytics which builds on transparent and understandable algorithms,
including explainable machine learning, combined with highly interactive
and powerful visualizations.
*Biography*: Christopher Collins is the Canada Research Chair in Linguistic
Information Visualization and an Associate Professor of Computer Science at
the University of Ontario Institute of Technology (UOIT). His research
focus is interdisciplinary, combining information visualization and
human-computer interaction with natural language processing, with a focus
on interaction design and guidance in visual analytics. While his group is
best known for text visualization, he collaborates across a wide variety of
topics, including health informatics, machine learning, and computer
security. His papers have been published in many venues including IEEE
Transactions on Visualization and Computer Graphics, have received awards
at IEEE VIS, and have been featured in popular media such as the CBS
News and the New York Times Magazine. Dr. Collins is a past member of the
executive of the IEEE Visualization and Graphics Technical Committee and
regularly serves on the IEEE VIS Conference Organizing Committee. He
received his PhD in Computer Science from the University of Toronto.