Difference between revisions of "FriendBook"

From Aicip
Jump to: navigation, search
Line 1: Line 1:
 
<h4>Abstract</h4><hr />
 
<h4>Abstract</h4><hr />
 +
 +
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.

Revision as of 17:50, 14 July 2012

Abstract


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.