Existing social networking services recommend potential friends to users based on their social graphs and web actions. This mechanism, however, may not be the most appropri- ate to reflect a user’s preferences on friend selection in real life. In this paper, we present Friendbook, a semantic-based friend recommendation system for social networks. By ex- ploiting recent sociology findings, Friendbook identifies and recommends users with similar life styles. Specifically, tak- ing the advantage of developments in text mining, Friend- book models a user’s daily life as life documents with the frequency of activity information, or bag-of-activity. Friend- book then extracts the life style distributions of users from their life documents using the Latent Dirichlet Allocation (LDA) algorithm. Based on these distributions, Friendbook constructs a friend-matching graph that represents users’ life style similarities. When users send queries to Friendbook for friend recommendations, the Friendbook server analyzes the friend-matching graphs, ranks users according to their impact, and sends a list of potential friends in response to the query. To further improve the accuracy of recommen- dations, Friendbook integrates a feedback mechanism that takes inputs from users, and dynamically adjusts internal parameters to optimize online performance. We have im- plemented Friendbook based on the Android-based Nexus S mobile phones, and evaluated its performance based on data collected from 8 users for a period of three months. The re- sults show that the recommendations accurately reflect the preferences of users in choosing friends.