Algorithm aims to break down social media echo chambers
Image credit: Dreamtime
Finnish and Italian researchers have created an algorithm they say is capable of breaking down barriers between groups of social media users with different political views.
As many internet users turn from consuming news directly from traditional news sources, they often turn to their social media feeds to stay up to date. This means that many are only reading opinions that align with their own views, and blocking out opposing viewpoints.
This is particularly true for issues that are highly controversial, such as issues relating to social justice. The rise of alternative news sources – which often present highly polarised material or misinformation – has become a topic of heated discussion, as social media companies begin to accept the influence of these sources on their users’ political opinions.
Now, a collaboration of researchers from Aalto University in Helsinki and the University of Rome Tor Vergata has created an algorithm intended to present social media users with a more balanced selection of content.
While investigating content shared by on social media relating to issues in the news, the researchers saw that users tended to form two separate circles of users talking about themselves, reinforcing their views.
“We use word clouds as a qualitative case study to complement our quantitative results, whereby words in the cloud represent the words found in the users’ profiles,” explained Kiran Garimella, a PhD student at Aalto University. “For instance, if we look at the topics related to the hashtag #russiagate, we can see not only that the two word clouds that represent the conflicting viewpoints are rather different, but also that they indicate either support or hate for Trump.”
For instance, in the instance of discussion about fracking, one group of users would tend to use terms associated with positive aspects of fracking, and another group using terms associated with negative aspects.
“There is small overlap in the keywords used by each side, indicating that users are in an echo chamber,” said Professor Aristides Gionis, a computer scientist based at Aalto Univeristy.
In order to combat this formation of echo chambers on social media, the researchers created an algorithm intended to expose users to views that may challenge their own.
The researchers used a ‘greedy’ algorithm: it selects the optimal choice at each stage, with the aim of finding an overall optimal solution, in this case, to maximise the number of users exposed to both sides of a debate. The algorithm selects a set of highly influential users, who may be encouraged to spread their more balanced opinions to groups of users with polarised views.
“Examining the content of those users we see that it uses terms from both sides of the discussion. Thus, these users can play a significant role in initiating a social debate and help spreading the arguments of one side to the other,” said Garimella.