A new study finds that among Twitter users, different online speech patterns divide the social network into linguistic “tribes.”
Led by scientists from Royal Holloway University in the UK and Princeton University, the research discovered that social networking groups can develop their own dialects and speech patterns, forming tribe-like communities.
“This means that by looking at the language someone uses, it is possible to predict which community he or she is likely to belong to, with up to 80 percent accuracy,” said Dr, John Bryden, who works at the School of Biological Sciences at Royal Holloway. “We searched for unusual words that are used a lot by one community, but relatively infrequently by the others. For example, one community often mentioned Justin Bieber, while another talked about President Obama.”
“When we started to apply John’s ideas, surprising groups started to emerge that we weren’t expecting,” Dr. Sebastian Funk of Princeton University told Phys Org. “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.”
The study, published in the EPJ Data Science journal, used cutting-edge algorithms to group users into communities. The algorithms found Twitter users that tended to message other members of their community, by focusing on public communication between users. The team then produced a map that connected these Twitter communities based on common jobs, political beliefs and hobbies.
“Interestingly, just as people have varying regional accents, we also found that communities would misspell words in different ways,” said Professor Vincent Jansen of Royal Holloway. "The Justin Bieber fans have a habit of ending words in ‘ee’, as in ‘pleasee’, while school teachers tend to use long words.”
The study can be found online here.
