Twitter has developed a way to measure how users feel about President Barack Obama and Republican candidate Mitt Romney. The “Twitter Political Index” or “TwIndex,” aims to provide real-time opinions based on the sentiment of user tweets, according to the National Journal.

TwIndex uses an algorithm to evaluate every single tweet in real time that mentions Obama or Romney and then assigns a sentiment score to each tweet based on the content. The index’s scale runs from zero to 100 and a higher number indicates more positive sentiment. Obama and Romney are also measured individually, not against each other, according to an article on Buzzfeed.

"It is a collection of key words, phrases, and patterns that is ever expanding what is positive and negative," Adam Sharp, the leader of Twitter's government, news, and social innovation team told the National Journal.

As the article also notes:

“The initial installment showed Obama with a score of 34 and Romney with 25, based on tweets posted on Tuesday. Since the TwIndex compares tweets about the candidates to all tweets on other topics, that means that tweets about Obama are on average more positive than 34 percent of tweets not mentioning him. It also means that tweets about Obama are generally more positive than tweets about Romney. The plan is for the latest Twitter Political Index to be posted each day at 8 p.m. at election.twitter.com.”

The TwIndex uses the growing science of sentiment analysis in which computers try to assess the meaning or feeling behind a piece of written content. The algorithm is pretty accurate, agreeing with a randomly selected human 90 percent of the time on what a Tweet means. However, the system still has trouble detecting sarcasm or irony, according to the article on Buzzfeed.

While sentiment analysis technology is improving, at Connections Media we believe real-time social media monitoring by a dedicated team yields the most accurate observations. Such tools can help support social media monitoring, but deriving real insight requires a human understanding of the digital conversation.