Methodology

FollowGraph is derived from analysis of social media following data from public social media accounts using PersonaLive. Each social account is geocoded and assigned a PersonaLive segment. Results are summarized for each variable over the 80 segments, providing average following rates for each segment.

For example, the variable “Pepsi” is computed using accounts that follow @Pepsi. Percentage of accounts that follow @Pepsi are calculated nationally and for each segment. These rates are applied at a household level using the segment classification of every household. This approach assumes that households with similar demographic, social, and mobile data characteristics tend to have similar following patterns.

Following rates are aggregated at a census block group (CBG) level across all households to estimate the total follow rate for all households in the CBG. This aggregated likelihood to follow is finally indexed to the national average (CBG follow rate divided by national follow rate). The result is a series of indices for geographic areas which measure the propensity of consumers to follow certain social media accounts relative to the national average.

Back to top