Twitter Political Index Measures Sentiment About Obama and Romney

  • Share
  • Read Later
Twitter

Happiness and rage: Twitter has both.

After trying to figure out which tweets are positive and which are negative, such “sentiment data” is being used to reflect the public’s general mood about certain topics. If you’re mad or glad about the Olympics, for instance, whatever you say on Twitter about the Games helps turn the London Eye Ferris wheel into a giant mood ring every night.

Twitter is using the same type of sentiment data for its new Twitter Political Index, which “evaluates and weighs the sentiment of Tweets mentioning Obama or Romney relative to the more than 400 million Tweets sent on all other topics,” according to Twitter’s blog post.

“For example,” says Twitter, “a score of 73 for a candidate indicates that Tweets containing their name or account name are on average more positive than 73 percent of all Tweets.”

Twitter contends that its Political Index is trying to reinforce – not replace — polling data from the likes of Gallup, but boasts that “the trend in Twitter Political Index scores for President Obama over the last two years often parallel his approval ratings from Gallup, frequently even hinting at where the poll numbers are headed.”

“But what’s more interesting are the periods when these data sets do not align,” says Twitter, “like when his daily scores following the raid that killed Osama bin Laden dropped off more quickly than his poll numbers, as the Twitter conversation returned to being more focused on economic issues.”

“By illustrating instances when unprompted, natural conversation deviates from responses to specific survey questions,” says Twitter, “the Twitter Political Index helps capture the nuances of public opinion.”

The Twitter Political Index can be found at election.twitter.com and is updated every day after 8pm Eastern. There’s historical data available for the candidates as well.

MORE: Want to Light Up the London Eye? Just Tweet That the Olympics Are ‘Totes Amazeballs’