New collaboration brings greater social data coverage to research, education, and commercial users.
Texifter, a text analytics start-up, is launching access to two new major blog data streams as part of its collaboration with Columbia University: the WordPress fire hose, which gives access to every comment or post on every WordPress blog, and the Disqus PowerTrack, both provided by Gnip, the world’s largest provider of social data.
“We provide the tools that allow Fortune 1000 companies and market research firms to analyze the massive amounts of unstructured data available from blogs, social media sites, surveys, and email,” says CEO Dr. Stuart Shulman. Dr. Shulman is also a political science professor and director of the Qualitative Data Analysis Program (QDAP) at the University of Massachusetts Amherst. “We are excited about the collaboration with Columbia University and the acquisition of two vibrant and important blog data streams.”
Texifter provides cost-effective web-based software for text analytics using unstructured data. Its flagship product, DiscoverText, is a cloud-based software solution that supports advanced filtering, clustering, human coding, and machine learning with unstructured text data. Commercial enterprises, education institutions, and government agencies use DiscoverText for storing and sifting through large amounts of social media data from sources like Facebook, Twitter, and Google+. DiscoverText users develop custom, reusable machine-learning text classifiers, which provide fast and valuable insights. The text analytics process reveals common themes in unstructured data as well as unique, infrequent, or unanticipated findings.
At Columbia University, researchers are utilizing these data to study the role of opinion leaders and other intermediaries in the spread of news links via social media.
“By using DiscoverText and Gnip data streams,” notes Dr. Augustin Chaintreau of the Computer Science Department, “we understand this behavior better and can model the role of social networks in creating contextual meaning around important news events.”
Founded in 2009, Texifter‘s current clients include: Google, Volvo, QVC-UK, the National Library of Norway, the US Fish and Wildlife Service, and the Comptroller of the Currency.