- BRW Lists
Published 12 June 2012 09:59, Updated 13 June 2012 05:05
Researchers have created an algorithm that can predict the success of a news tweet with 84 per cent accuracy.
The University of California, Los Angeles (UCLA) and Hewlett-Packard’s HP Labs cooked up the algorithm for a research paper titled The Pulse of News in Social Media: Forecasting Popularity, and reached the conclusion that for tweets – as with many things – clear, simply communication wins.
According to the study, which specifically examines tweets by news organisations, the four keys to success are the news source publishing the tweet, the topic (or category) the tweet covers, the subjectivity of the language and people or organisations named in the tweet.
“We have taken into account four features that cover the spectrum of the information that can be gleaned from the content – the source of the article, the category, subjectivity in the language and the named entities mentioned,” the researchers write.
“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.”
The Atlantic digs out a June 8 New York Times tweet to illustrate how the elements come together: “Bits Blog: Apple Buddies Up With Cheaper Wireless Partners for iPhone”.
“If that seems a little dull for Twitter perfection … well, that’s the point. Steadiness — compelling news expressed in straightforward, not hyperbolic, language — is actually a component of a maximally effective tweet, according to the algorithm,” The Atlantic’s Megan Garber writes.
“And this particular tweet is also sent from a credible source, The New York Times, making it extra spreadable. It’s also about technology, the most popular, shareable category of news story. It’s engaging without being insistent. And it stars a company — Apple — with high name recognition.”
While the UCLA-HP research focused on news tweets it’s likely the rules of clarity, directness and brand recognition apply to other business-oriented tweets just as well.