Communications of the ACM
New Research Discovers the Emergence of Twitter 'tribes'
Credit: Royal Holloway, University of London
Users of social network sites such as Twitter are forming tribe-like communities, according to a new project led by scientists at Royal Holloway, University of London, and Princeton University. Their research reveals that the communities have a common character, occupation, or interest, and develop their own distinctive languages.
The communities often use unusual words and misspell words in different ways. Based on the language people use, the researchers were able to predict which community they belong to with up to 80 percent accuracy, says Royal Holloway's John Bryden. The researchers produced a map of the communities showing how they have vocations, politics, ethnicities, and hobbies in common. They also used algorithms to group Twitter users into communities. The algorithms functioned by seeking individuals that tend to send messages to other members of the same community. Bryden then suggested analyzing the language use of the uncovered communities.
"Surprising groups started to emerge that we weren't expecting," notes Princeton's Sebastian Funk. "One 'anipals' group was interested in hosting parties to raise funds for animal welfare, while another was a fascinating growing community interested in the concept of gratitude."
From Royal Holloway, University of London
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found