Rhetoric that evokes moral values on Twitter may signal whether a protest will turn violent, according to a study led by researchers from the University of Southern California (USC). The study was published on May 23 in the journal Nature Human Behaviour.

The USC researchers found that people are more likely to endorse violence when they moralize the issue that they are protesting—that is, when they see it as an issue of right versus wrong. That holds true when they believe that others in their social network moralize the issue, too.

“Extreme movements can emerge through social networks,” said the study’s corresponding author, Morteza Dehghani. “We have seen several examples in recent years, such as the protests in Baltimore and Charlottesville, where people’s perceptions are influenced by the activity in their social networks. People identify others who share their beliefs and interpret this as consensus. In these studies, we show that this can have potentially dangerous consequences.”

The scientists analyzed 18 million tweets posted during the 2015 Baltimore protests over the death of 25-year-old Freddie Gray, who died as police took him to jail. Using a method to detect moralized language on Twitter, the researchers investigated the association between moral tweets and arrest rates, a proxy for violence. This analysis showed that the number of hourly arrests made during the protests was associated with the number of moralized tweets posted in previous hours.

Tweets containing moral rhetoric nearly doubled on days when clashes among protesters and police became violent.

Social Media Posts as a Barometer for Activism

Social media sites such as Twitter have become a significant platform for activism.

Recent examples of movements tied to social media include the #marchforourlives effort to seek gun control, the #metoo movement against sexual assault and harassment, and #blacklivesmatter, a campaign against systematic racism that began in 2014 after the police-involved shooting death of 19-year-old Michael Brown in Ferguson, Missouri.

An example involving more violence is the Arab Spring revolution, which began in Tunisia in late-2010 and set off protests in Egypt, Libya and other nations, forcing changes in their leadership. In Syria, clashes escalated into a war that has killed hundreds of thousands of people and displaced countless refugees.

Detecting Moralization Online

The scientists developed a model for detecting moralized language based on a framework that can reliably identify text that evokes moral concerns. The “Moral Foundations Theory” defines these dueling values:

• Care/harm

• Fairness/cheating

• Loyalty/betrayal

• Authority/subversion

• Purity/degradation

Here are two examples of moralized language and the foundations with which they are associated:

Tweet: Why does the opposition speak only abt black on black crime as a rebuttal to police brutality/murder? #AllCrimeMatters, right? #FreddieGray

Moral Foundations: Fairness and Loyalty

Tweet: regardless of how anyone feels, prayers to the police force and their family

Moral Foundations: Care and Purity

Moralization and political polarization are exacerbated by online “echo chambers,” researchers say. These are social networks where people connect with other like-minded people while distancing themselves from those who do not share their beliefs.

Why More Protests Are Violent

Social media data help researchers illuminate real-world social dynamics and test hypotheses, explained Joe Hoover, a lead author of the paper and doctoral candidate in psychology at the USC Dornsife College of Letters, Arts and Sciences. “However, as with all observational data, it can be difficult to establish the statistical and experimental control that is necessary for drawing reliable conclusions.”

To make up for this, the scientists conducted a series of controlled behavioral studies, each with more than 200 people. Researchers first asked participants to read a paragraph about the 2017 clashes over the removal of Confederate monuments in Charlottesville, Virginia. Then the researchers asked how much participants agreed or disagreed with statements about the use of violence against far-right protesters.

The more certain people were that many others in their network shared their views, the more willing they were to consider the use of violence against their perceived opponents, the scientists found.