Dear all,
We hope you can join us this Wednesday, May 1, 2013 from 12-1.30pm for the
last session of the Applied Statistics Workshop this semester. It will be
held in CGIS Knafel 354. Molly Roberts <http://scholar.harvard.edu/mroberts>,
Brandon Stewart <http://scholar.harvard.edu/bstewart>, and Dustin
Tingley<http://scholar.harvard.edu/dtingley>ey>,
all from the Department of Government at Harvard University, will give a
presentation entitled "Topic models for open ended survey responses with
applications to experiments". A light lunch will be served at 12 pm and the
talk will begin at 12.15
Abstract:
Despite broad use of surveys and survey experiments by
political science,
the vast majority of survey analysis deals with responses to options along
a scale or from pre-established categories. Yet, in most areas of life
individuals communicate either by writing or by speaking, a fact reflected
in earlier debates about open and closed ended survey questions. Despite
good reasons to collect and analyze open ended data, it is relatively rare
in the discipline and almost exclusively done through a process involving
human coding of survey responses. We present an alternative, semi-automated
approach, the Structural Topic Model (STM) (Roberts et al. 2013), that
draws on recent developments in machine learning based analysis of textual
data. A crucial contribution of the method is that it incorporates
information about the text, such as the author's gender, country of origin,
treatment status, or when something was written. This paper focuses on how
the STM is extremely helpful for descriptive, exploratory, or inferential
purposes for survey researchers and experimentalists. The STM makes
analyzing open ended responses easier, more revealing, and capable of being
used to estimate treatment effects. We illustrate these innovations with
several experiments.
A draft version of the paper is available
here<http://scholar.harvard.edu/files/dtingley/files/topicmodelsopenende…
.
An up-to-date schedule for the workshop is available at
http://events.iq.harvard.edu/events/node/1208.
Best,
Konstantin
--
Konstantin Kashin
Ph.D. Candidate in Government
Harvard University
Mobile: 978-844-0538
E-mail: kkashin(a)fas.harvard.edu
Site:
http://www.konstantinkashin.com/<http://people.fas.harvard.edu/%7Ekkashi…