Newscasts

PNS Daily Newscast - May 21, 2018 


Giuliani now says the Mueller probe into whether President Trump obstructed the Russian collusion inquiry will end by September. Also on the rundown: Healthcare providers gear up as Trump's new "Gag Rule" targets Planned Parenthood; and some perspective on the administration’s push for Arctic oil.

Daily Newscasts

Predicting TN Political Sentiments With Twitter

Computer scientists have created a program that may unlock some knowledge of the country's political pulse through Twitter. (Esther Vargas/flickr.com)
Computer scientists have created a program that may unlock some knowledge of the country's political pulse through Twitter. (Esther Vargas/flickr.com)
November 7, 2016

NASHVILLE, Tenn. – Americans have learned a lot through Twitter about how Donald Trump feels about some people, but how do Twitter users feel about Donald Trump?

Computer scientists have developed what they call sentiment analysis software that can determine how someone feels based on what he or she writes or says.

Feifei Li helped develop the program, and says it provides a real-time window into how the public is reacting to political events.

"What's cool is that you can actually adjust the lens of the window,” he states. “If you look at the last few months of data altogether, the sentiments for Democrats is stronger than the sentiments for Republicans. Given the recent outburst of email scandals, things might change a little bit."

Researchers say the biggest surge of positive tweets for Republicans came during their national convention, and again after a video was released of Trump boasting about sexually assaulting women. The peak for both positive and negative tweets for Democrats came on the heels of the final debates.

In Tennessee, election hours on Tuesday will vary by county, but voters will be allowed to vote if they are in line at the time the poll closes.

Li's team started with more than 250 million global tweets and used advanced software to identify 1.6 million political posts in the United States.

Li notes the program was only able to detect the leanings of Twitter users, which are not reflective of the population at large.

The group's results suggest that if larger data streams can be tapped in future versions, today's pollsters could find themselves out of a job.

"We feel like if you collect enough data from the population, if you get an unbiased sample from the population using this data-driven approach, the results might be more accurate," he states.

The scientists used artificial intelligence and machine learning to help the program decipher complexities in human language. The group then compared its results with The New York Times' forecasts and found the state-by-state analysis was very similar.



Stephanie Carson, Public News Service - TN