TweetCast – What you tweet says a lot about your politics and who you are going to vote for in this highly volatile presidential election.
TweetCast, a new online tool, is able to predict with 80 percent accuracy who will vote for Donald Trump and who will vote for Hillary Clinton.
Try TweetCast. Can it correctly predict who you support?
Perhaps more surprising, the tool can also predict which states will go blue or red (Democrat or Republican).
Since its founding by Will Thomson and Chip Russell in June 2016, the Massif Capital Real Asset Strategy has outperformed all of its real asset benchmarks. Since its inception, the long/short equity fund has returned 9% per annum net, compared to 6% for the Bloomberg Commodity Index, 3% for the 3 MSCI USA Infrastructure index Read More
Tweeting the words “lying,” “liberal,” “illegal” and “money,” for example, indicates a vote for Trump. Using the words “single,” “humanity,” “rights” and “y’all,” on the other hand, predicts a vote for Clinton.
“These are not the most prevalent terms that voters use on Twitter,” says Larry Birnbaum, professor of computer science in Northwestern University’s McCormick School of Engineering. “They are the most predictive terms.”
TweetCast uses a machine-learning algorithm to examine words, hashtags, tagged usernames, and mentioned websites to uncover which terms are most predictive of voting preference.
“TweetCast is a good example of what we can tell about you from Twitter.”
Birnbaum’s team did not develop the algorithm used in TweetCast, but they are the first to apply the approach to determining political preferences by analyzing tweets.
Birnbaum and his students first launched a version of TweetCast for