You are here:  Home  >  Data Education  >  BI / Data Science News, Articles, & Education  >  Current Article

Using Semantic Analysis to Predict the President

By   /  March 15, 2012  /  No Comments

Karen Hanna recently posed the question, can Twitter predict the President?

Karen Hanna recently posed the question, can Twitter predict the President? She explained, “Some data analysts are looking at political sentiment in social media data to make predictions around the presidential campaigns. Attensity looked at 800,000 Tweets from February 25 through March 2 and measured ‘positive sentiment and share of voice for each candidate.’ Attensity determined that Romney would win seven states, Gingrich would win Georgia, Paul would win Alaska, and Santorum would take Vermont. Attensity was asked by USA Today to analyze Twitter data to predict how voting would go on Super Tuesday. Attensity is a social analytics company based in Palo Alto. Like other social media analytics companies, it is interested in how text analysis techniques might be applied to data collected from social media to enhance market research capabilities.”

Hanna continues, “Using social data in a predictive sense may come well after understanding how and why users engage in the online conversation in the first place. For midsized business, the takeaways from this experiment is in how the candidates use social media and the everyday discoveries made through analytics. USA Today quotes Zac Moffet, digital director of the Romney campaign, as saying, ‘Facebook helps you find your most engaged members of the community.’ Businesses that use analytics to find their own engaged customers gain an understanding of how their business is affected by that engagement. From a day-to-day perspective, this is information that is valuable to know.”

Read more here.

Image: Courtesy Attensity

You might also like...

Evolving Cloud Networks and How to Keep Them Secure

Read More →