Bridging Political Divides With Artificial Intelligence | Duke Today – Duke Today

Sociologist builds AI chatbot to help mediate heated political discussions
Want to have more productive conversations on social media? Maybe a chatbot can help.
New research from Duke sociologist Christopher Bail and a team of Brigham Young University colleagues used artificial intelligence to intervene and improve conversations online. The team built an AI chat assistant to mediate conversations between two people on opposite sides of the ongoing gun control debate. When one participant was about to send a message, the chat assistant – or ‘chatbot’ – would rephrase the language, with evidence-based science on conflict mediation, to present a more constructive version of the person’s argument to the other participant.
The results were encouraging. Bail says the exercise led the participants to understand and allow the expression of opposing viewpoints in the political system in general, and not just in the context of their single conversation partner.
And importantly, it didn’t strip either participant of their own agency. Once the chatbot edited a question or answer, the participant could choose whether to send it or keep their own original version.
With AI use growing at a pace and ubiquity that makes many folks nervous, Bail says this experiment suggests the technology can be a force for good.
He spoke to Duke Today about the research, which was published in August in the Proceedings of the National Academy of Sciences. Here are excerpts:
Q: In your new study, an AI chatbot serves as a communication intermediary between two people on different sides of an issue. The chatbot evaluates the language of a question and tweaks it to be constructive to the person receiving the question. What is the basic logic and hypotheses behind creating this experiment?
BAIL: Though debate on social media can seem like a lost cause, there is a large scientific literature that identifies the factors that produce more productive conversations about controversial topics, such as the one we studied (gun control). There are also many non-profit groups that work to implement these evidence-based strategies on the ground. But these interventions are just a drop in the bucket, since getting people who disagree to meet up in person – and recruiting a skilled mediator to facilitate their discussion – is very difficult. My co-authors and I wondered: What if AI could serve as a kind of conflict mediator that nudges people to implement the type of strategies a human facilitator might recommend—such as “active listening” or the practice of rehearsing someone else’s argument back to them to demonstrate that you have heard them.
Q: How might this device work in real digital life, outside the structure of a research project?
BAIL: We are still in early days with generative artificial intelligence, and much more research is needed before we can let tools such as GPT-4 run wild on our platforms. At the same time, many social media companies are currently exploring how to use such tools to decrease toxicity and perform content moderation—especially since many of the people who performed these tasks previously were recently laid off at large companies such as Facebook and Twitter. My co-authors and I want to ensure that such efforts are informed by scientific evidence—and we believe our work is a first step in this direction.
Q: What is the chatbot providing to the conversation that the two human participants are not providing themselves?
BAIL: Anyone who has been in an argument has trouble explaining why things got out of hand. Very often, there are simple explanations—people do not feel heard, they feel disrespected, or they feel like they are talking past the person they are arguing with. Arguments can escalate because of 1, 2 or all three of these reasons. Our intervention simply nudges people to use communicative tactics that make each of these outcomes less likely.
Q: In this role, is your chatbot corrective in nature? Meaning, are people generally inclined towards online nastiness or bias that needs correcting?
BAIL: Our chatbot was not designed to pull people back from the brink after they have already been arguing. Instead, it is designed to structure conversations so that their overall trajectory is more productive, less stressful, and is more likely to include a genuine exchange of ideas.
Q: It seems so much political conversation on social media is done in bad faith, using misinformation or deception, that people simply aren’t interested in an honest discussion. Is this a consideration for you?
BAIL: So many people are focused upon the dangers of generative AI on social media— and there are clear and present dangers related to misinformation. At the same time, very few people are focused on the other side of the coin: how can we use AI to nudge people in the other direction, perhaps before they become susceptible to misinformation or other polarizing behaviors. There has been so much focus on the dark side of generative AI, that we risk overlooking a major opportunity to leverage these powerful new tools to enable the braver angels of our nature.

October 25, 2023

October 23, 2023

Read on Duke Global Health Institute
October 18, 2023

Read on Divinity School
September 12, 2023
More than a year of activities and events will highlight Duke’s past and propel university into its second century
Duke Today is produced jointly by University Communications and Marketing and the Office of Communication Services (OCS). Articles are produced by staff and faculty across the university and health system to comprise a one-stop-shop for news from around Duke. Geoffrey Mock of University Communications is the editor of the ‘News’ edition. Leanora Minai of OCS is the editor of the ‘Working@Duke’ edition. We welcome your comments and suggestions!