19 hours ago by
HP Labs says it’s possible to know if your tweet will be a dud before you type the 140 characters.
Researchers have developed a formula that predicts the number of
times a news “article will be tweeted with surprising accuracy.” The
researchers predicted tweet popularity with 84% accuracy based on
ranking news articles by four criteria.In the new study called “The Pulse of News in Social Media: Forecasting Popularity, HP Labs used a statistical model to rate the popularity of 40,000 news articles published during nine days in August 2011.
The statistical model considered four things when evaluating the popularity of the article: 1. the source of the news article; 2. the category of news; 3. whether the article was emotional or objectively written; and 4. name dropping. For example, mentioning Lady Gaga in an article can increase the likelihood the story will be successful on Twitter. The study found that an article’s emotional or objective tone did little to sway its popularity.
“HP Labs’ study reinforces the intuition that the source of news matters most in determining how many tweets will link to a given article,” HP said in a statement. “But as social media continues to increase in importance, key questions remain about how users are influenced to act – beyond clicking the ‘retweet’ button – and the nature of journalism in 140 characters.”
Watch the video to learn more about the study.
No comments:
Post a Comment
Note: Only a member of this blog may post a comment.