A new study claims it can predict the popularity of a news story on Twitter with an 84 percent accuracy rate by looking solely at four factors that affect content.
The study, led by Bernardo Huberman of the Social Computing Lab Group at the Palo Alto-based HP Labs, examined the content of an article before it was published in determining how popular it would be on Twitter.
Specifically, the authors looked at:
- The news source that generates and posts the article;
- The category of news the article falls under;
- The subjectivity of the language in the article;
- The people and things mentioned in the article.
“Our results show that while these features may not be sufﬁcient to predict the exact number of tweets that an article will garner, they can be effective in providing a range of popularity for the article on Twitter,” Huberman wrote in the study. “We achieved an overall accuracy of 84% using classiﬁers.”
The study, however, raises a lot of questions for journalists.
Would you change what you wrote about if you knew specifically what would factor into its popularity on sites such as Twitter? Then again, should Twitter and Facebook popularity even matter when it comes to news stories? Will news stories from different networks become more and more similar as news organizations fight for social media supremacy?
A post on Technology Review’s Physics arXiv Blog brings up two interesting pros and cons on the study’s implications:
It’s not hard to imagine an automated article checker–rather like the grammar checkers in word processing programs–that reads articles and predicts how popular they are likely to be when published.
In a sense, that’s what journalists do now when they choose topics to write about. But this process is entirely intuitive, based as much on gut feel as on a good understanding of the dynamics of the audience. Huberman’s algorithm could automate this process.
That would have profound effects on the generation of news stories. On the one hand, it could lead to the homogenisation of stories as news organisations focus on optimising their stories for this algorithm.
On the other hand, automation could lead to a new generation of more tightly written and better focused stories that build on the new algorithm and better it.
Huberman claims it is important to predict the popularity of news stories before publication to foster “the possibility of appropriate decision making to modify an article and the manner of its publication.” But is this really the case?
It would be dangerous if news organizations gave too much importance to the popularity of stories on Twitter and its counterparts. In a worst-case scenario, this could lead to some news not being shared because it was deemed “unpopular.” News should be told even if it won’t be popular in 140 characters or less.
What do you think about the implications of this study?