gistfile1.txt

---------- Forwarded message ----------
From: Daniel Bauer <@cs.columbia.edu>
Date: Thu, Feb 21, 2013 at 6:19 PM
Subject: Mon 2/25 - Brendan O'Connor
To: nlp-announce
Cc: Brendan O'Connor <brenocon@cmu.edu>


Dear all,

Brendan O'Connor from CMU will be our speaker at the NLP meeting next Monday.

TIME: Mon 02/25/2013, 1:30pm
LOCATION: CS Conference Room (CSB 453)

Hope to see you there!
Daniel

###
Brendan O'Connor (CMU/Harvard): Text Data Analysis in Political Science and
Sociolinguistics

ABSTRACT:
What can text analysis tell us about society?  Enormous corpora of news, social
media, and historical documents record events, beliefs, and culture.  While
manual content analysis is a useful and established social science method,
interest in automated text analysis has exploded in recent years, since it
scales to massive data sets, and can assist in discovering patterns and themes.

I will present two case studies of using text analysis as a measurement
instrument for social phenomena: (1) Extracting events between international
actors from news text, using temporal and dyad political context as a prior for
learning latent event classes; and (2) Examining Twitter to answer questions
about how language changes -- what are the geographic and demographic
determinants linguistic influence?  Recurring themes include language analysis
as a statistical indicator of population-level variables, and latent state
temporal modeling of textual time series.

Given time and audience interest, I'm also happy to talk about syntactic
analysis of social media text, sentiment analysis and opinion polls, or
analyzing Chinese censorship in microblogs.

BIO:
Brendan O'Connor (http://brenocon.com/) is a Ph.D. Student at Carnegie Mellon
University's Machine Learning Deptartment, advised by Noah Smith, and is
currently a Visiting Fellow at Harvard's Institute for Quantitative Social
Science.  He is interested in machine learning and natural language processing,
especially when informed by or applied to the social sciences.  He has interned
in the Facebook Data Science group, and worked on crowdsourcing at Crowdflower
/ Dolores Labs, and "semantic" search at Powerset.  His undergraduate degree
was Symbolic Systems.