[ChimeText] 17Jul (tomorrow!) : Doug Oard / Fourth-Generation Content Analysis: Supporting social science research using computational linguistics

[Min-Yen Kan]

A reminder about Doug Oard's talk tomorrow.  Please come! I know it's
early and on the other side of the campus...  Cheers, -M

Speaker: Doug Oard, University of Maryland
Title: Fourth-Generation Content Analysis: Supporting social science
research using computational linguistics
Date: Thursday 17 Jul, 10:30am-12nn
Venue: Executive Classroom (SoC1 05-48)

ABSTRACT:

Babbie defines content analysis as "the study of recorded human
communications such as books, Web sites, paintings and laws." We all
practice what we might call "first generation" content analysis every
time we read a paper. What we might call "second generation" content
analysis involves social scientists who develop coding frames
appropriate to their research question and then meticulously annotate
a collection of moderate size in order to support their analysis.
Third-generation content analysis leverages extensive automation in
fairly straightforward ways, such as by counting words or preparing a
concordance. We now find ourselves on the verge of a fourth generation
of content analysis techniques in which computational linguistics
holds promise for automated population of complex coding frames. This
could enable sophisticated Web-scale studies, potentially fostering
emergence of research methods that go well beyond content to encompass
many forms of evidence from human interaction with information. In
this talk, I will describe some challenges that we must overcome as
these two communities learn to work together. I'll illustrate my talk
with examples from the PopIT procect collaboration between social
scientists and computational linguists at the University of Maryland
in which we are developing automated tools for computational analysis
of trends in the popularity of information technology innovations.
I'll start with a sketch of our research design for working at the
intersection of these two fields, and then I'll describe a few
specific pieces of that puzzle that we have already started to build.

Finally, I'll conclude with a few remarks about where we see potential
for collaboration with others who share similar interests.

BIODATA:
Douglas Oard is Associate Dean for Research at the College of
Information Studies of the University of Maryland, College Park, where
he holds joint appointments as Associate Professor in the College of
Information Studies and in the Institute for Advanced Computer
Studies. He earned his Ph.D. in Electrical Engineering from the
University of Maryland. Dr. Oard's research interests center around
the use of emerging technologies to support information seeking by end
users, with recent work focusing on interactive techniques for
cross-language information retrieval, searching conversational media,
and leveraging observable behavior to improve user modeling. Together
with Ping Wang and Ken Fleischmann, he helps to lead the NSF-funded
PopIT project. Additional information is available at
http://www.glue.umd.edu/~oard/

Upcoming talks:
18 Jul: (related seminars) 3 seminars on 1) Real-Time Document Image
Retrieval with LLAH 2) Large-Scale and Real-Time Specific Object 3)
Pattern recognition with supplementary information
25 Jul: Yahoo! Research Labs talks:
4 talks on 1) Evgeniy Gabrilovich / Overview of Computational
Advertising 2) Rosie Jones / Geography in Web Search 3) Donald Metzler
/ Predicting when (not) to Advertise 4) Vanessa Murdock / Diversifying
Image Search with User Generated Content