Room #TBC | Pieter de la Court Gebouw | Wassenaarseweg 52 | Leiden
About 20,000 influential individuals and organizations are thought to dominate the current micro-blogging forum of choice, Twitter. As a result, more people are finding reasons to follow, gather, and analyze the streams of hyper-textual digital consciousness produced by these oracles. Beyond the influential thought leaders in every domain, there is a growing army of content curators and producers who collectively are the long tail of the Twitter crowd. Computer science students love the data; it is big and can be very rich with network and linguistic clues. This talk is about how and why to gather, filter, search, human code, and machine classify the Twittersphere. Dr. Shulman has developed and commercialized software, DiscoverText, providing the human language power tools required for the Twittersphere.
STU SHULMAN / SPEAKER
Stu Shulman (@stuartwshulman) is a scholar, inventor of DiscoverText, entrepreneur, D-level soccer coach, proud dad/son, CEO of Texifter, and Taoist garlic grower. Texifter builds web-based text analytics for individuals, groups, and crowds. Founded in 2009 after a decade of NSF-funded research, Texifter delivers collaborative power tools for sorting text. Social data, email, voice of the customer or employee, and other sources are collected over APIs or uploaded via spreadsheets. The flagship application is DiscoverText, which allows users to access Gnip Power Tracks for Twitter, Tumblr, WordPress, and Disqus.