Debating a stubborn opponent can be an exhausting task, unless, of course, your entire argument is automated.
A software developer has created a Twitter bot that automatically discovers and responds to tweets that are skeptical of global warming.
Nigel Leck’s chatbot @AI_AGW, who goes by the name “Turing Test,” scans Twitter every five minutes in search of hundreds of terms and phrases that tend to be used by those who think global warming is not occurring or that humans are not responsible for it.
Once the bot finds such a phrase, it tweets a relevant 140 character response.
The bot chooses a response from a database of hundreds of pre-written rebuttals, which often include links to information and videos.
According to Leck, the database originally was just a collection of responses he had written himself, but now the responses include arguments culled from a university source whom he cannot divulge.
Many of those who receive a tweet from @AI_AGW do not realize it is a bot and try to start an argument with it, Leck says.
Nothing identifies the tweets as autoresponses, although Leck has left a clue for those familiar with Stanley Kubrick’s “2001: A Space Odyssey.”
“If [the chatbot] actually argues them into a corner, it tends to be two crowds out there,” says Leck. “There’s the guns and God crowd, and their parting shot will be ‘God created it that way’ or something like that. I don’t know how you answer that.”
The bot has one serious flaw – it cannot detect sarcasm, at least not yet. For example, the bot responded to tweets such as “It’s 113 degrees outside – good thing global warming’s a myth!” that occurred during a heatwave in Los Angeles.
Leck said the bot includes an algorithm that allows it to learn to recognize such false positives.