A New Online Tool Predicts Your Vote
A new online tool can now predict your candidate for the coming US election in the basis of voters’ Tweet language.
Thanks to TweetCast, the online tool can predict your vote in the election and which states will go blue or red as well.
How does it work?
According to Larry Birnbaum, a Northwestern University computer scientist and one of the creators of the online tool, tweeting the words “lying,” “liberal,” “illegal” and “money,” for example, indicates a vote for Republican nominee, Donald Trump. Meanwhile, tweet languages such as “single,” “humanity,” “rights” and “y’all,” predict a vote for Democratic candidate, Hillary Clinton.
Birnbaum said, “These are not the most prevalent terms that voters use on Twitter. They are the most predictive terms.”
Birnbaum and his students first launched a version of TweetCast for the 2012 presidential election. The tool was included in PBS MediaShift Idea Lab’s “Our Picks for the Most Innovative Election Coverage.”
TweetCast Predicts Your Votes With 80% Accuracy
The makers of the TweetCast emphasized that one’s tweet says a lot about one’s politics, particularly in the coming presidential election.
Whether you are going to vote for Trump or Clinton, the TweetCast can predict your vote with 80% accuracy as well.
Interestingly, aside from its ability to predict your vote, the tool also predicts which states will go blue or red (Democrat or Republican).
TweetCast Can Predict Which States Go Blue or Red
TweetCast uses a machine-learning algorithm to examine words, hashtags, tagged usernames and mentioned websites to know which terms are most predictive and prevalent of voting preference among Twitter users.
In addition, 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).
