There's a special logic to the flow of posts on a forum or message board, one that's easy to parse by someone who's spent a lot of time on them but kinda hard to understand for those who haven't.
Researchers at UCLA are working on teaching computers to understand these structured narratives within chronological posts on the web, in an attempt to get a better grasp of how humans think and communicate online.
"Our question was, could we devise computational methods to discover an emerging narrative framework underlying internet conversations that was possibly influencing the decision making of many people throughout the country or possibly world?" Timothy Tangherlini, who describes himself as a "computational folklorist".
Tangherlini and his team built an algorithm to review 1.99 million posts from two different parenting forums. The posts came from 40,056 users and spanned nine years ending in 2012. Most of the users identified themselves as mothers.
The researchers focused in on posts about vaccines. "The anti-vaccine movement was a clear candidate for this type of study," Tangherlini said.
"Tens of thousands of parents were exchanging ideas about child-rearing online and, through those interactions, creating virtual communities where they could share concerns, propose methods to allay those concerns, and share their own experiences."
From the data, they were able to identify that huge numbers of parents were going online to talk about vaccines, their perceived health risks, distrust of institutions that require them, and ways to get exemptions for their children.
Vwani Roychowdhury, a machine learning expert who worked on the algorithm, said: "It's especially impressive, when you take into consideration the fact that all the machine was fed with, were just web pages, nothing else; and it found all the vaccine related concepts all on its own."
While this study was targeted at conversations around vaccination, the researchers say the same principles could be applied to any topic. Down the line, they hope it could allow for false narratives to be identified as they develop and countered by targeted messaging.
Roshan Bastini, a professor of health policy who also contributed to the research, said: "We hope to utilize findings from this work to design and test interventions that may positively influence vaccination rates because they are more likely to address some of the key drivers of resistance."