Twitter Is Going the Academic Route to Measure Its Public Conversation Health Efforts

Over 230 responses to its March RFP yielded two winning groups

Twitter turned to the academic world for measurement help - Credit by elenabs/iStock
Headshot of David Cohen

Twitter revealed the winners of the request for proposals it issued in March to devise ways to measure the overall health of public conversation on its network.

The social network said in March that nonprofit research organization Cortico developed four indicators to measure conversational health—shared attention, shared reality, variety of opinion and receptivity—and it was looking to expand on those and “identify indicators of conversational health that are even more specific to Twitter and its impact.”

After reviewing more than 230 responses via a committee that included representatives from the company’s engineering, product, machine learning, data science, trust and safety, legal and research teams and whittling the total to 50 and then 16, Twitter arrived at a pair of winners.

One group of academics will examine echo chambers and uncivil discourse and develop two sets of metrics focused on how communities form around political discussions and the challenges that these discussions may spur.

The group will be led by Leiden University assistant professor of political science Rebekah Tromble and include Leiden’s Michael Meffert, Syracuse University’s Patricia Rossini and Jennifer Stromer-Galley, Delft University of Technology’s Nava Tintarev and Bocconi University’s Dirk Hovy.

Legal, policy and trust and safety lead Vijaya Gadde and director of product management, health David Gasca detailed what the group will work on in a blog post: “Based on their past findings, echo chambers—which form when discussions involve only like-minded people and perspectives—can increase hostility and promote resentment towards those not having the same conversation. The project’s first set of metrics will assess the extent to which people acknowledge and engage with diverse viewpoints on Twitter. The second set of metrics will focus on incivility and intolerance in Twitter conversations. The group has found that while incivility, which breaks norms of politeness, can be problematic, it can also serve important functions in political dialog. In contrast, intolerant discourse—such as hate speech, racism and xenophobia—is inherently threatening to democracy. The team will therefore work on developing algorithms that distinguish between these two behaviors.”

And University of Oxford’s Miles Hewstone and John Gallacher and University of Amsterdam’s Marc Heerdink will team up to tackle the issue of bridging gaps between communities on Twitter.

Gadde and Gasca wrote, “The project builds on Prof. Hewstone’s long-standing work to study intergroup conflict. When the communication between groups contains more positive sentiments, cooperative emotions and more complex thinking and reasoning from multiple perspectives, prejudice is reduced and relations can improve. This was previously demonstrated in a variety of contexts, including in post-conflict community building efforts in Northern Ireland, as well as in online communities. As part of the project, text classifiers for language commonly associated with positive sentiment, cooperative emotionality and integrative complexity will be adapted to the structure of communication on Twitter.”

They concluded, “Ensuring that we have thoughtful, comprehensive metrics to measure the health of public conversation on Twitter is crucial to guiding our work and making progress, and both of our partners will help us continue to think critically and inclusively so we can get this right. We know this is a very ambitious task, and we look forward to working with these two teams, challenging ourselves to better support a thriving, healthy public conversation.” David Cohen is editor of Adweek's Social Pro Daily.