Professor Lu Wang from Northeastern University believes that improving the quality of debates currently taking place across all of social media is achievable through the right combination of artificial intelligence (AI), linguistic analysis and data visualization, ultimately leading to more valuable debates.

Whereas much of what is taking place in the social media realm is hate-filled and negative, Wang hopes to transform social media into a venue for constructive conversations. The first step to achieving that, according to Wang, is understanding how a persuasive argument is fashioned.

"Debates should be mechanisms for discovering something new about the world," said Nick Beauchamp, assistant professor of political science at Northeastern and a collaborator on the project. "The hope is that you would come away from a debate not with just a set of new facts you learned, but also with a better way of thinking about the problem."

As such, Wang and Beauchamp have developed an algorithm that locates the strongest characteristics of an argument. Then Beauchamp and Wang applied the algorithm to a dataset of over one hundred Oxford-style debates, where the winner was determined by which side had successfully swayed a greater portion of the audience to their cause. Once applied, the algorithm predicted the debate winner in almost 75 percent of the debates.

Looking at the data, the algorithm determined that debates where “we” and “they” were used more often were more successful than when “you” and “I” appeared in an argument.

Likewise, debate winners were also able to keep topics focused on their strongest point. In fact, the team believed that this was one of the greatest predictors of whether someone would be a debate victor.

In terms of how to use this algorithm, Wang and Beauchamp hope to one day take it to Twitter and Facebook for the purpose of developing an automatic tool designed to measure the quality of debates taking place there.

"Our tool might be able to help keep debates constructive when certain groups are dominating the conversation while other opinions are being ignored," Wang said.