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.
The tool, developed by researchers Northwestern University in the US, can also predict which party will dominate a particular state in the November 8 elections.
Tweeting the words "lying," "liberal," "illegal" and "money," for example, indicates a vote for Republican candidate Trump.
"These are not the most prevalent terms that voters use on Twitter. They are the most predictive terms," said Larry Birnbaum, professor at Northwestern.
Also Read
TweetCast's prediction accuracy of voter preference is 80 per cent, researchers said.
The algorithm was trained on Twitter users who have publicly declared support for one of the two candidates.
During training, the algorithm found patterns in those user's activity and applied those patterns to users across Twitter.
For this presidential election, Birnbaum and Jason Cohn, a PhD student at Northwestern, expanded the tool to predict the states Trump will take and the states Clinton will take.
Based on those user's 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, researchers said.
"TweetCast is a good example of what we can tell about you from Twitter. 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 will vote for," Birnbaum said.
Disclaimer: No Business Standard Journalist was involved in creation of this content