Andrea Ceron
How pollsters could use social media data to improve election forecasts
[Commentary] Donald Trump’s Nov 8 victory surprised almost everyone. But if pollsters had looked at Twitter, they might have recognized that the race was close — or so we learned in our recent research. Even when polls were showing a big lead for Hillary Clinton, real-time analysis of social media was showing it getting tighter — even if you subtract the propaganda bots used by Trump staff, estimated to make up about 20 to 30 percent of the total volume of pro-Trump social media traffic.
Public opinion has profoundly changed. And the way to measure it must change as well. Social media information offers useful signals about public sentiment. Catching them is the challenge for those who study and predict politics.
[Andrea Ceron is assistant professor of political science at the University of Milan and co-founder of VOICES from the Blogs. Luigi Curini is associate professor of political science at the University of Milan. Stefano M. Iacus is professor of statistics at the University of Milan.]