Brendan T. O'Connor
I am an assistant professor in the
College of Information and Computer Sciences
at University of Massachusetts, Amherst
(since Fall 2014).
I am affiliated with the
Computational Social Science Institute,
the Initiative in Cognitive Science,
the Centers for
Data Science and
Intelligent Information Retrieval.
See the SLANG Lab page.
What can statistical text analysis tell us about society?
that can help answer social science
I'm interested in
statistical machine learning and
natural language processing,
especially when informed by or applied to areas like
political science or sociolinguistics.
My work often uses text data from news and social media.
See also my (oldish) research statement
or publications below.
If you are interested in getting involved in research, shoot me an email.
There is a rich set of other faculty at UMass interested in
areas from computational social science
to natural language processing.
See the Computational Social Science Institute (CSSI) website,
and this list of computation+language researchers and courses.
I finished my PhD in 2014
Carnegie Mellon University's
Machine Learning Department,
where I was advised by
Noah A. Smith.
I have also been a
Visiting Fellow at Harvard IQSS,
interned with the Facebook Data Science team.
Before grad school,
I worked on crowdsourced annotations at CrowdFlower / Dolores Labs,
as well as
"semantic" search at Powerset.
I was an undergrad and masters student in the Stanford
Symbolic Systems Program (cognitive science, more or less).
Some recent talks
- Demographic bias in social media language analysis: a case study of African-American English.
At the Network Science Institute,
Northeastern University, December 14, 2016.
A Little Bit of NLP Goes A Long Way:
Adding Phrases to the Term-Document
Matrix using Finite-State Shallow Parsing.
Seventh Annual New Directions in Analyzing Text as Data,
October 15, 2016.
- Panelist, "Fairness and Machine Learning for Educational Practice" at NCME 2016 (the Annual Meeting of the National Council on Educational Measurement, April 9, 2016, Washington, D.C.). Talk title: "Opening the ML black box: Why and what is my algorithm doing?"
- Is a minority dialect “noisy text”?:
Social media NLP, analysis, and variation
invited talk at ACL 2015 Workshop on Noisy User-generated Text
(See also Google Scholar.)
Other papers on my CV or
Proceedings of WWW 2017.
PLOS-ONE, November 2014.
- Also arXiv:1210.5268; an earlier version was from Oct. 2012 and poster at NIPS 2012 Workshop on Social Network and Social Media Analysis.
PhD Thesis, Carnegie Mellon University, 2014.
ACL Workshop on Interactive Language Learning, Visualization, and Interfaces, June 2014. (Proceedings of ACL 2014.)
In SemEval-2014 (Proceedings of the International (COLING) Workshop on Semantic Evaluations, Dublin, Ireland, August 2014).
Proceedings of ACL 2013.
Proceedings of ACL 2013.
Proceedings of NAACL 2013
arXiv:1310.1975, Oct 2013.
Data Analysis Project report, Machine Learning Department, CMU.
In Linguistic Annotation Workshop, 2013.
In First Monday 17.3, March 2012.
In NIPS Workshop on Comptuational Social Science and the Wisdom of Crowds, Sierra Nevada, Spain, December 2011.
In Proceedings of EMNLP 2011.
In ACL-2011 (short paper).
In NIPS-2010 Workshop on Machine Learning and Social Computing.
In Proceedings of
EMNLP 2010 (presentation).
- Press coverage:
New York Times,
All Things Considered,
Wall Street Journal,
San Francisco Chronicle,
In ICWSM-2010 (presentation).
In ICWSM-2010 (demo track).
In Beautiful Data, ed. Toby Segaran and Jeff Hammerbacher. O'Reilly Media. 2009.
In EMNLP-2008 (presentation).
- MiTextExplorer: interactive exploration of text data and document covariates.
- TweetNLP: tokenization and part-of-speech tagging for Twitter.
- ARKref, a coreference resolution system.
- ParseViz - quick and dirty parse tree/dependency visualization via graphviz.
- tsvutils for tab-separated data processing
- Other misc utilities (commandline, R, Python...)
Recent and not-so-recent news
- Aug 19: Thesis defense.
- Mar 28: invited speaker, University of Michigan School of Information.
- Mar 26: invited speaker, NYU
Courant Institute and
Center for Data Science.
- Feb 26: invited speaker, Allen Institute for Artificial Intelligence.
- Feb 24-25: invited speaker, Information School, University of Washington. slides, abstract.
- Feb 14: invited speaker, Microsoft Research, New York City.
- Feb 10-11: invited speaker, Computer Science, UMass Amherst.
- Feb 7: invited speaker, Information Science, Cornell University.
- Jan 27: invited speaker, Toyota Technological Institute at Chicago, University of Chicago.
- Jan 15, 2014: invited speaker, Wharton Statistics, University of Pennsylvania. slides, abstract.
- Oct 9, 2013: invited talk at Univ. of Maryland at College Park,
CLIP Colloquium (host: Philip Resnik). [slides]
- Summer 2013: attended SOCS, NAACL, and ACL. See publications list for presentations/posters.
- Apr 9: Thesis proposal has been proposed: "Statistical Text Analysis for Social Science."
- Mar 22: invited speaker, Northeastern (Lazer Lab; host David Lazer)
- Feb 25: invited speaker, Columbia NLP group (abstract)
Elsewhere on the Internet
My PGP key
Random links: JK 1995
There are many Brendan O'Connors in the world.
If this is the wrong webpage, you may be interested in another Brendan O'Connor – for example,
My awesome sister, Maureen O'Connor, is a writer in New York.