Nieman Foundation at Harvard
HOME
          
LATEST STORY
An AI chatbot helped Americans who believe in conspiracy theories “exit the rabbit hole”
ABOUT                    SUBSCRIBE
March 3, 2014, 12:38 p.m.
LINK: docs.google.com  ➚   |   Posted by: Caroline O'Donovan   |   March 3, 2014

I am newly returned from Baltimore and the NICAR conference, where one of the most laugh-out-loud sessions of the weekend involved Brian Abelson, Joe Kokenge and Abraham Epton talking about how and why to build Twitter bots. Stephen Suen, of MIT’s Comparative Media Studies writing program, has a helpful blog post about the conversation.

Kokenge laid out the basics of making a bot. Epton talked about his ILCampaignCash, a Chicago Tribune product that tracks and tweets campaign donations. Abelson offered a long list of bots both humorous (like @FloridaMan or @Haikugrams) and practical (like @TreasuryIO or @YourRepsOnGuns) that suggested the breadth of possibility when it comes to bots. There are also, of course, challenges:

Brian says the logic behind the Twitter bot is strict rather than greedy. He also points to issues faced with Times Haiku. “The challenge is, how are we not going to make a haiku of the Syrian civil war, how are we not going to make a haiku of something that’s serious… that’s why it’s easier to do some of these funny artistic ones rather than something you can put the name of a newsroom on.”

Once again, rate limiting is brought up — Abraham says you can write the logic of your bot to avoid having your account get deleted. “Use common sense,” he says. The more you avoid behaviors that make your bot seem like a spam bot, the safer your account will be. Joe and Brian agree — the rate limit is high enough that you can get away with a tweet every 5 minutes without hitting it.

Show tags
 
Join the 60,000 who get the freshest future-of-journalism news in our daily email.
An AI chatbot helped Americans who believe in conspiracy theories “exit the rabbit hole”
“It still works even for people who strongly distrust AI.”
Documentary filmmakers publish new AI ethics guidelines. Are news broadcasters next?
The Archival Producers Alliance’s new generative AI guardrails put audience transparency first.
Mobile newsrooms help drive citizen journalism in North Macedonia and beyond
“With each region we visited, the audience from that region grew, and they have continued to follow us to this day.”