See all NewsEngineering News

TweetCast Predicts Your Vote

Online tool predicts how individuals and states will vote in the upcoming presidential election based on users’ tweets

Whether you realize it or not, what you tweet says a lot about your politics.

Launching today, TweetCast can predict if a Twitter user will vote for Donald Trump or Hillary Clinton in the 2016 US presidential election. The online tool’s prediction accuracy is 80 percent.

Larry BirnbaumDeveloped by Northwestern Engineering’s Larry Birnbaum and his students, TweetCast uses an algorithm to examine words, hashtags, tagged usernames, and mentioned websites to uncover which are most predictive of voting preference. 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,” said Birnbaum, professor of computer science in Northwestern’s McCormick School of Engineering. “They are the most predictive terms.”

The algorithm was trained on Twitter users who have publicly declared support for one of the two candidates. It found patterns in those users’ activity and applied those patterns to users across Twitter. Although Birnbaum’s team did not develop TweetCast’s algorithm, it is the first to apply this approach to determining political preferences by analyzing tweets.

Birnbaum and his students also launched a version of TweetCast for the 2012 presidential election, which was included in PBS MediaShift Idea Lab’s “Our Picks for the Most Innovative Election Coverage.” For this year’s election, Birnbaum and his PhD student Jason Cohn expanded the tool to predict how states will vote. By using Twitter’s geo-location feature, the algorithm randomly sampled approximately 80,000 Twitter users from each state. Based on those users’ predictive words, TweetCast could make a prediction for which states will most likely vote blue (New York, California, and Illinois, for example) or red (Mississippi, Arkansas, and Texas). 

TweetCast is still experimental and has encountered some issues. States with fewer Twitter users, such as Wyoming and Montana, are trickier to predict. Birnbaum also points out that Twitter users skew young and liberal. His team is currently working with machine-learning expert Douglas Downey, associate professor of computer science, to explore ways to compensate for these biases.

One can imagine how TweetCast’s information can help campaigns target voters and use Twitter to push voter turnout. But Birnbaum said it also shows that many of our preferences can be gleaned from Twitter.

“TweetCast is a good example of what we can tell about you from Twitter,” he said. “We can determine a lot from the language you use, including which restaurants you like, books you read, sports you enjoy, news you consume — and who you’ll vote for.”