Computer Science

Document Type

Conference Proceeding

Publication Date



Social media has become part of modern news reporting, used by journalists to spread information and find sources, or as a news source by individuals. The quest for prominence and recognition on social media sites like Twitter can sometimes eclipse accuracy and lead to the spread of false information. Could we use the so-called "wisdom of crowds" to detect the likelihood that some claim spreading may be true or false? This paper, part of an ongoing research, offers evidence that most of the time, false claims do not spread like true ones, and that the reaction of the audience following a story on Twitter is correlated with the validity of the story. Using the system, we have examined the spreading patterns of a number of claims that have been discussed in the news by investigative journalists. Here, we first introduce two new metrics for measuring the spreading and skepticism around the propagation of a claim. Then, employing a classification algorithm that takes into account the behavior of the crowd posting or retweeting about a story, our system leads us to observe that true and false rumors have different footprints in terms of how they propagate and invoke skepticism by their audience. In particular, we observe that, more often than not, false rumors are more likely to be negated if exposed to a large audience.


WebScience 2015 poster