| 摘要 |
A social networking system may enable advertisers to target advertisements to users interested, in varying levels of intensity, in concepts, locations, pages, and other objects on the social networking system. Targeting criteria for advertisements may include explicit interest intensity levels in selected objects. Using past histories of user engagement, location information, and social graph information, a social networking system may generate a predictive model to estimate interest intensity levels of users in the selected objects. Advertisements may be targeted and provided to users based on interest intensity using the predictive model.
|
