We interviewed researchers at the University of Illinois Chicago in the Health Media Collaboratory about their use of DiscoverText and the Gnip-enabled Power Track for Twitter to study smoking behavior. The team, led by Dr. Sherry Emery, explains why it is important to train and use custom machine classifiers to sort the millions of tweets they are collecting from the full Twitter fire hose. The UIC team strongly argues for the combination of good tools and highly reliable data.

We interviewed researchers at the University of Illinois Chicago in the Health Media Collaboratory about their use of DiscoverText and the Gnip-enabled Power Track for Twitter to study smoking behavior. The team, led by Dr. Sherry Emery, explains why it is important to train and use custom machine classifiers to sort the millions of tweets they are collecting from the full Twitter fire hose. The UIC team strongly argues for the combination of good tools and highly reliable data.

We interviewed researchers at the University of Illinois Chicago in the Health Media Collaboratory about their use of DiscoverText and the Gnip-enabled Power Track for Twitter to study smoking behavior. The team, led by Dr. Sherry Emery, explains why it is important to train and use custom machine classifiers to sort the millions of tweets they are collecting from the full Twitter fire hose. The UIC team strongly argues for the combination of good tools and highly reliable data.

A high-level summary of techniques we use to sift the Target brand references from all other used of the common word target on social media.

Introduction to deduplication and clustering of public comments using DiscoverText.

A very short introduction to creating a new project in DiscoverText.

Simple steps to sort raw Twitter feeds from the public API by sender.

Brief intro on how to use a free DiscoverText account and the Twitter public API to start collecting Twitter tweets for research purposes.

A talk prepared in late October 2012, but never delivered due to Hurricane Sandy. It has three parts. Part One is about fear and loathing in US political history. Part Two is about the social campaign trail. Part Three reports on new tools and techniques we developed using DiscoverText to study political fear.

A new feature lets users create "Defined Searches" which are reusable multi-term searches that can help isolate certain types of documents in a corpus.