Predicting the Strength of Ties Through Social Media
Posted by Bill Ives on Fri, Mar 12, 2010
Eric Gilbert and Karrie Karahalios at the University of Illinois at Urbana-Champaign recently published an interesting paper on Predicting Tie Strength With Social Media. Building on the theoretical work on strong and weak ties started by the classic Mark Granovetter 1973 paper “The Strength of Weak Ties,” they looked at whether social media behavior could be used as a predictor of tie strength. In this paper the researchers present a predictive model that maps social media data to tie strength. The model builds on a dataset of over 2,000 Facebook relationships and distinguishes between strong and weak ties with over 85% accuracy.
They asked 35 people to rate a number of their Facebook friends that were randomly selected. Then they looked at the Facebook behavior of these people to see if could accurate predict the strength of their ties as reported by the participants. Dimensions such as the use of words associated with intimacy and intensity, duration of communication, social distance, and other factors were looked at for their predictive power. The complete set of variables was combined to form the predictive model that worked in 85% of the instances.
I am sure that the researchers would be the first to agree that more work needs to be done. As a former researcher I can see many potential confounding variable but, at the same time, the work looks promising. They offer some practical applications. For example, a “system that prioritizes via tie strength, or allows users to tune parameters that incorporate tie strength, might provide more useful, timely and enjoyable activity streams.”
This is especially true as many people are building friends or followers that number in the hundreds, if not thousands. This would also apply within the enterprise as the use of social media within the firewall continues to grow.