Researchers Develop an Internet Truth Machine 87
Hugh Pickens writes "Will Oremus writes that when something momentous is unfolding—the Arab Spring, Hurricane Sandy, Friday's horrific elementary school shooting in Connecticut—Twitter is the world's fastest, most comprehensive, and least reliable source of breaking news and in ongoing events like natural disasters, the results of Twitter misinformation can be potentially deadly. During Sandy, for instance, some tweets helped emergency responders figure out where to direct resources. Others provoked needless panic, such as one claiming that the Coney Island hospital was on fire, and a few were downright dangerous, such as the one claiming that people should stop using 911 because the lines were jammed. Now a research team at Yahoo has analyzed tweets from Chile's 2010 earthquake and looked at the potential of machine-learning algorithms to automatically assess the credibility of information tweeted during a disaster. A machine-learning classifier developed by the researchers uses 16 features to assess the credibility of newsworthy tweets and identified the features that make information more credible: credible tweets tend to be longer and include URLs; credible tweeters have higher follower counts; credible tweets are negative rather than positive in tone; and credible tweets do not include question marks, exclamation marks, or first- or third-person pronouns. Researchers at India's Institute of Information Technology also found that credible tweets are less likely to contain swear words (PDF) and significantly more likely to contain frowny emoticons than smiley faces. The bottom line is that an algorithm has the potential to work much faster than a human, and as it improves, it could evolve into an invaluable 'first opinion' for flagging news items on Twitter that might not be true writes Oremus. 'Even that wouldn't fully prevent Twitter lies from spreading or misleading people. But it might at least make their purveyors a little less comfortable and a little less smug.'"
Cultural bias? (Score:5, Insightful)
This is really interesting research, but it's also based on one event in one country.
Conclusions based on what may be language or cultural norms (such as "did you phrase in the positive or the negative") might not translate to other locales well (e.g. Hurricane Sandy in the US).
But, then, that's what's great about science. Testable predictions we can apply to data.
Rating individual tweets, accurate? (Score:5, Insightful)
Re:Truth? Whose? (Score:5, Insightful)
Reality is the stuff that doesn't go away when you stop believing it.
Don't be a pedantic asshole. We can't determine the absolute truth, but we can get a close enough approximation.
Looking for disaster, just look at car commercials (Score:3, Insightful)
There's a basic problem here. (Score:3, Insightful)
The basic problem with any such approach is that tweets are individual opinions and you cannot arrive at the truth or falsehood of objective facts by analyzing a collection of he-saids and she-saids.
The hospital is either on fire or it is not on fire, regardless of what anybody says.
Re:I wonder... (Score:5, Insightful)
I correctly judged the credibility of the "Iraq has WMDs" based mostly on the tone of original news reports.
We had information from UN weapons inspectors stating they were able to go wherever they wanted and examine whatever they wanted and so far had not found any evidence of a currently-active program or any stockpiles of usable weapons. The tone of these reports was direct and devoid of pleas to emotion.
The White House labeled these reports "not helpful" and directed the public's attention to historic atrocities and put forward innuendo regarding alleged Iraqi support for terrorists. It certainly looked like fearmongering. The very fact that the WH was labeling actual current information from Iraq as "not helpful" was to me the most damaging to their case. If they were interested in the truth, I reasoned, current information from international inspectors could only be helpful.
Re:Researchers Develop an Internet Truth Machine (Score:2, Insightful)
Sure, but most people tweeting false info in a disaster are just stupid kids (or man-children) who think its funny. They're probably not going to put lots of effort into it, because then it wouldn't be fun.
Re:Cultural bias? (Score:5, Insightful)
It's a popular denier meme: 1998 was a very hot year and if you start your data series there you can show an overall decline.
Viewed on any other scale, this artifact goes away. But it doesn't matter how many times you tell deniers about that; they know what story they want to tell and will continue to cherry pick the data to tell it.