Verena Erlenbusch-Anderson, associate professor of philosophy in the College of Arts and Sciences, wrote an op-ed for History News Network titled “Confronting ‘Who We Are.’” Erlenbusch-Anderson specializes in political philosophy and often teaches courses on the philosophy of law. After…
‘Share of Voice’ Project Provides Glimpse Behind the Curtain of Social Media Data in Election Coverage
Newhouse School assistant professor Jennifer Grygiel, working in collaboration with the School of Information Studies, is the lead on a new project that examines the use of social media data in the coverage of the 2016 presidential election, particularly the debates.
The Election Share of Voice Project utilizes social media analytics software Sysomos and its MAP function to look at posts for top campaign hashtags #MAGA (Trump) and #ImWithHer (Clinton), as well as mentions of the Twitter handles @realDonaldTrump and @HillaryClinton.
The goal is to provide transparency regarding the generation of social data charts, which are often presented live by the networks during the debates, and to illuminate some of the problems associated with such charts.
“Twitter uses keywords to filter and measure their data, but if the keywords are not inputted correctly, or are biased, the share of voice metric will not be accurate,” says Grygiel, who earlier this year authored a blog post for The Huffington Post that outlined the ways in which simple errors can affect the reliability such data. “News data partners such as Twitter, Facebook and Google need to release their share of voice methodology so that people and journalists can verify the accuracy of their analysis. This is especially true if the data are being presented in a way that leads someone to believe this metric is a sign of voting intent or popularity. It’s important to keep in mind that share of voice is only a read of volume and that sentiment analysis is not being conducted.”
The project, which will provide updated Twitter metrics daily, may also help to outline best practices for compiling social data, and serve as a resource for journalists wishing to use Twitter share of voice information in their reporting.