Joshua Garland and Mirta Galesic discuss their research on hate speech and counter-hate speech.

In a special presentation for the online ScienceWriters2020 conference in October, Joshua Garland and Mirta Galesic of the Santa Fe Institute presented the first large-scale analysis of tens of millions of instances of hate and counter-hate speech on Twitter.

Their preliminary findings, which have not yet been peer-reviewed, suggest that organized movements to counteract hate speech on social media are more effective than striking out on one’s own. 

“I’ve seen this big shift in civil discourse in the last two or three years towards being much more hateful and much more polarized,” says Garland, a mathematician and Applied Complexity Fellow at SFI. “So, for me, an interesting question was: what’s an appropriate response when you’re being cyber-bullied or when you’re receiving hate speech online? Do you respond? Do you try to get your friends to help protect you? Do you just block the person?” 

To study such questions scientifically, researchers must first have access to a wealth of real-world data on both hate speech and counter-speech, and the ability to distinguish between the two. That data existed, and Garland and collaborator Keyan Ghazi-Zahedi at the Max Planck Institute in Germany found it in a three-year interaction that played out over German Twitter: As an alt-right group took to the platform with hate speech, an organized movement rose up to counter it.

“The beauty of these two groups is they were self-labeling,” explains Galesic, the team’s social scientist and a resident professor at SFI. She says researchers who study counter-speech usually have to employ hundreds of students to hand-code thousands of posts. But Garland and Ghazi-Zahedi were able to input the self- labeled posts into a machine-learning algorithm to automate large swaths of the classification. The team also relied on 20-30 human coders to check that the machine classifications matched up with intuition about what registers as hate and counter-speech.

The result was a dataset of unprecedented size that allows the researchers to analyze not just isolated instances of hate and counter-speech, but also compare long-running interactions between the two.

“Now we can resolve this massive data set from 2016 to 2018 to see how the proportion of hate and counter-speech changed over time, who gets more likes, who is retweeted, and how they replied to each other” Galesic says.

The quantity of data, a tremendous boon, also makes it “incredibly complex,” Garland notes. The researchers are in the process of comparing tactics for both groups and pursuing broader questions such as whether certain counter-speech strategies are more effective than others.

“What I’m hoping is that we can come up with a rigorous social theory that tells people how to counter hate in a productive way that’s non-polarizing,” Garland says, “And bring the Internet back to civil discourse.”  

Read the article, "Could organized counter-speech curb online hate?" on the website for the Council for the Advancement of Science Writing (November 4, 2020)

Video from the presentation will be made public in November 2020. Check back here for the link or follow us on Twitter @sfiscience.