[Ml-stat-talks] Monday 5/23 at 3PM, Jordan Boyd-Graber
blei at CS.Princeton.EDU
Fri May 20 15:47:02 EDT 2011
jordan boyd-graber, once a graduate student in our CS department, returns
for one day from his post at UMD. his talk sounds fascinating. it looks to
be of particular relevance to those of you interested in topic models
(especially for exploration and political data), large scale data analysis,
and keeping humans in the loop. see the full announcement below.
Interacting with Large Datasets and Discovering Topic Influencers
University of Maryland, College Park
Computer Science Room 402
Monday, May 23 at 3:00PM
Abstract: Imagine you need to get the gist of what's going on in a large
dataset such as all tweets that mention Obama, all e-mails sent within a
company, or all newspaper articles published by the New York Times in the
Topic models, which automatically discover the themes which permeate a
are a popular tool for discovering what's being discussed. However, topic
models aren't perfect; errors hamper adoption of the model, performance in
downstream computational tasks, and human understanding of the data.
humans can easily diagnose and fix these errors. We present a statistically
sound model to incorporate hints and suggestions from humans to iteratively
refine topic models to better model large datasets.
We also examine how topic models can be used to understand topic control in
debates and discussions. We demonstrate a technique that can identify when
speakers are "controlling" the topic of a conversation, which can identify
events such as when participants in a debate don't answer a question, when
pundits steer a conversation toward talking points, or when a moderator
her influence on a discourse.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Ml-stat-talks