Follow My Friends This Friday! An Analysis of Human-Generated Friendship Recommendations

Online social networks support users in a wide range of activities, such as sharing information and making recommendations. In Twitter, the hashtag #ff, or #followfriday, arose as a popular convention for users to create contact recommendations for others. Hitherto, there has not been any quantitative study of the effect of such human-generated recommendations. This paper is the first study of a large-scale corpus of human friendship recommendations based on such hashtags, using a large corpus of recommendations gathered over a 24 week period and involving a set of nearly 6 million users. We show that these explicit recommendations have a measurable effect on the process of link creation, increasing the chance of link creation between two and three times on average, compared with a recommendation-free scenario. Also, ties created after such recommendations have up to 6% more longevity than other Twitter ties. Finally, we build a supervised system to rank user-generated recommendations, surfacing the most valuable ones with high precision (0.52 MAP), and we find that features describing users and the relationships between them, are discriminative for this task.