Study Finds Algorithm That May Help Stymie Political Polarization
AALTO, Finland — Many people are disconnecting from their favorite social networks to escape the vicious back-and-forth between Democrats and Republicans following President Trump’s election. Now it seems social media could be the key to healing the divide after all, as a new study finds an algorithm that might help curb the tension seemingly splitting the country.
To combat political polarization, researchers at Aalto University in Finland have created an algorithmic technique that aims to bridge the gap between Hillary Clinton and Donald Trump supporters by connecting them and evaluating their Twitter use.
The study, recognized as the best student-paper in the Tenth International Conference on Web Search and Data Mining, creates algorithms in hopes of curbing polarization between those furthest apart politically, according to a university release.
“The main algorithm is based on the finding that for a special type of network simulating a polarized network, the best bridges we can add to [it] are between the nodes with the highest degrees on either side,” said professor Aristides Gionis from the Aalto University Department of Computer Science.
The research, which dealt with retweet networks, concluded that bringing closer users with the most followers would be best, but is impractical. To mend this, it is suggested bridging the gap between lesser known — but still popular — Twitter users.
“When applied on Twitter discussions around the US election results, the algorithm suggests that creating a bridge between @hillaryclinton and @breitbartnews would reduce polarization the most,” said Kiran Garimella, one of the researchers, in the statement. “However, taking into account how likely such a bridge is to materialize, the algorithm suggests that other bridges between less prominent Twitter accounts, for instance liberal journalist @mtracey and conservative activist @rightwingangel show better potential.
The research team plans to move from who to target in terms of bridging gaps to what will actually mend them when conducting future studies, according to the statement.