Bernardo Huberman and colleagues at Hewlett-Packard's Social Computing Lab have developed an algorithm that can predict how popular new stories will become.
Journalists rely on their gut feeling and their understanding of the dynamics of their audience when they choose to write about topics, but the algorithm could automate this process.
During a single week last August, the team examined the content of news stories and scored each article on the news source that generates and posts the article, the category of news, the subjectivity of the language, and the people and things named in the article. They measured the way the stories spread across the Twitter network to see which became popular and how quickly, then determined how an article's score in each criterion is linked to its eventual popularity.
"Our experiments show that it is possible to estimate ranges of popularity with an overall accuracy of 84 percent considering only content features," the team says.
The research could impact how articles are written and edited. News organizations could homogenize their stories to optimize them for the algorithm, but automation also could lead to more tightly written and better focused articles.
From Technology Review
View Full Article
Abstracts Copyright © 2012 Information Inc. , Bethesda, Maryland, USA
No entries found