[Colloquium] REMINDER: 5/22 TTIC Colloquium: Aron Culotta, Illinois Institute of Technology

[Mary Marre via Colloquium]

When:     Monday, May 22nd at 11:00 a.m.

Where:    TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526

Who:      Aron Culotta, Illinois Institute of Technology


Title:
Observational studies from social media using robust text classification
and learning from label proportions

Abstract:
Observational studies conducted with online social internet data have the
potential to provide insights into human sciences such as public health,
sociology, political science, and marketing. A key difficulty is that the
variables of interest are rarely observed and so must be estimated by
classification models that use features from user-generated text or social
connections. In this talk, I will discuss two lines of research to support
this approach. First, since it is critical that classifiers are not biased
by socio-economic or demographic variables, I will present a method to
train a text classifier while controlling for such covariates, even when
they are unobserved. Second, because user demographics are rarely observed,
and labeled training data is difficult to obtain, I will present a Learning
from Label Proportions (LLP) approach that trains a demographics classifier
from sets of users paired with population statistics (e.g., from the U.S.
Census). Finally, I will discuss a recent co-training method for LLP that
uses deep learning to combine text features with a user's profile image to
predict demographics.

Bio:
Aron Culotta is an Assistant Professor of Computer Science at the Illinois
Institute of Technology in Chicago, where he leads the Text Analysis in the
Public Interest lab (http://tapilab.github.io/). He obtained his Ph.D. in
Computer Science from the University of Massachusetts, Amherst in 2008,
where he developed machine learning algorithms for natural language
processing. He was a Microsoft Live Labs Fellow and completed research
internships at IBM, Google, and Microsoft Research. His work has received
best paper awards at AAAI and CSCW. He is Managing Editor of JMLR and an
SPC member for AAAI and ICHI.


Host: Kevin Gimpel <kgimpel at ttic.edu>


For more information on the colloquium series or to subscribe to the
mailing list, please see http://www.ttic.edu/colloquium.php

Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 504*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*

On Mon, May 15, 2017 at 10:51 PM, Mary Marre <mmarre at ttic.edu> wrote:

> When:     Monday, May 22nd at 11:00 a.m.
>
> Where:    TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526
>
> Who:      Aron Culotta, Illinois Institute of Technology
>
>
> Title:
> Observational studies from social media using robust text classification
> and learning from label proportions
>
> Abstract:
> Observational studies conducted with online social internet data have the
> potential to provide insights into human sciences such as public health,
> sociology, political science, and marketing. A key difficulty is that the
> variables of interest are rarely observed and so must be estimated by
> classification models that use features from user-generated text or social
> connections. In this talk, I will discuss two lines of research to support
> this approach. First, since it is critical that classifiers are not biased
> by socio-economic or demographic variables, I will present a method to
> train a text classifier while controlling for such covariates, even when
> they are unobserved. Second, because user demographics are rarely observed,
> and labeled training data is difficult to obtain, I will present a Learning
> from Label Proportions (LLP) approach that trains a demographics classifier
> from sets of users paired with population statistics (e.g., from the U.S.
> Census). Finally, I will discuss a recent co-training method for LLP that
> uses deep learning to combine text features with a user's profile image to
> predict demographics.
>
> Bio:
> Aron Culotta is an Assistant Professor of Computer Science at the Illinois
> Institute of Technology in Chicago, where he leads the Text Analysis in the
> Public Interest lab (http://tapilab.github.io/). He obtained his Ph.D. in
> Computer Science from the University of Massachusetts, Amherst in 2008,
> where he developed machine learning algorithms for natural language
> processing. He was a Microsoft Live Labs Fellow and completed research
> internships at IBM, Google, and Microsoft Research. His work has received
> best paper awards at AAAI and CSCW. He is Managing Editor of JMLR and an
> SPC member for AAAI and ICHI.
>
>
> Host: Kevin Gimpel <kgimpel at ttic.edu>
>
>
> For more information on the colloquium series or to subscribe to the
> mailing list, please see http://www.ttic.edu/colloquium.php
>
>
>
>
>
> Mary C. Marre
> Administrative Assistant
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 504*
> *Chicago, IL  60637*
> *p:(773) 834-1757 <(773)%20834-1757>*
> *f: (773) 357-6970 <(773)%20357-6970>*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20170521/d018b9c2/attachment.html>