We stand with Ukraine

Obama vs. Romney on Language: The three debates

23 October 2012

23 Oct 2012

Expert System, the semantic technology company, today released its findings from the comprehensive analysis of the language of President Barack Obama and Governor Romney in the presidential debates. The results highlight the language choices by the candidates as seen through semantic and linguistic analysis conducted by Expert System using the Cogito semantic platform.

Analysis Hightlights

Over the course of the debate, Romney was the more talkative, using an average of 14% more words than Obama. Romney’s word choices centered around the concepts of “taxes”, “plans” and “programs”, within which “people”, “job/work” and “America” were most frequently used. Obama spoke most often around the concepts of “business” and “labor”, where he most frequently used the action verbs “do” and “make” more than any other terms.

Among the people cited, Obama spoke most often of Osama Bin Laden, followed by Gaddafi (reflecting on his foreign policy achievements). Former U.S. presidents were also regularly mentioned, George W. Bush most frequently in general, while presidents Lincoln and Eisenhower were most often cited by Obama, with Romney recalling Roosevelt and Reagan. Behind the United States, China was the second-most mentioned nation by both candidates, with Iraq (Obama) and Iran (Romney) in third place. Libya got more attention in the last two debates, but was more often cited by Obama (ranking behind Massachusetts) than by Romney.

Al-Qaeda was the organization most often cited by Obama, while Romney referred to terrorist groups such as the Afghan Haqqani Network, likely to counter the success of Obama by highlighting revolutionary groups still in action.

“The upcoming elections in the U.S. have resulted in some very interesting analysis,” said Luca Scagliarini, VP Strategy & Business Development, Expert System. “This analysis focused only on the topics and concepts mentioned by the candidates, and while it is by no means a predictor, we believe that the semantic analysis of content will help anyone better understand and deal more effectively with any type of information.”