[tc_aol_on code=”519621912″]
Sad, mad, glad, confused about the presidential race so far? Well, if you are really lost on who to vote for, IBM may have a solution, depending on your mood.
Watson Elections, one of the surprisingly few political applications for IBM’s supercomputer, debuted on stage this morning at TechCrunch’s Disrupt Hackathon in Brooklyn, New York to help us decided the best candidate fitting our feelings.
If you are angry and disgusted right now, you may want to go for Donald Trump. A little less angry and just sadder fits a vote for Bernie Sanders.
Of course, if you are really happy right now, Trump also fits the bill.
Watson Elections uses natural language processing based on what each candidate said in the press to determine their overall mood. Hillary Clinton seems to be on the low end of all feelings, with much more neutral language, for example.
Two IBM researchers, Nikos Anerousis and Jinho Hwang, came up with the application after pulling an all-nighter at our Hackathon.
Join 10k+ tech and VC leaders for growth and connections at Disrupt 2025
Netflix, Box, a16z, ElevenLabs, Wayve, Hugging Face, Elad Gil, Vinod Khosla — just some of the 250+ heavy hitters leading 200+ sessions designed to deliver the insights that fuel startup growth and sharpen your edge. Don’t miss the 20th anniversary of TechCrunch, and a chance to learn from the top voices in tech. Grab your ticket before doors open to save up to $444.
Join 10k+ tech and VC leaders for growth and connections at Disrupt 2025
Netflix, Box, a16z, ElevenLabs, Wayve, Hugging Face, Elad Gil, Vinod Khosla — just some of the 250+ heavy hitters leading 200+ sessions designed to deliver the insights that fuel startup growth and sharpen your edge. Don’t miss a chance to learn from the top voices in tech. Grab your ticket before doors open to save up to $444.
The two tell me they’d eventually like to throw a few other features into the application. Whether or not a candidate is lying would be one. Another would be to eventually predict who’s got the job based on voter sentiment.
And there’s still a lot to iron out in the app to make sure it’s working. It was just drummed up overnight, after all.
“The thing with these models is you need an accurate training set,” Anerousis said. “You still have to validate some of the output here and verify what is real.”
