Title: Discovering Leaders from Community Actions
<br>
<br>
PRESENTER: Amit Goyal<br>
TIME: Thu Oct 9, 2pm<br>
LOCATION: room 304<br>
<br>
<br>
Reference:
Amit Goyal, Francesco Bonchi, Laks V.S. Lakshmanan, */Discovering
Leaders from Community Actions/*, To appear in Proc. of the 17th
Conference on Information and Knowledge Management, CIKM 2008, Napa
Valley, California, 2008.*
<br>
<br>
Abstract:
We introduce a novel frequent pattern mining approach to discover
leaders and tribes in social networks. In particular, we consider social
networks where users perform actions. Actions may be as simple as
tagging resources (urls) as in del.icio.us, rating songs as in Yahoo!
Music, or movies as in Yahoo! Movies, or users buying gadgets such as
cameras, handhelds, etc. and blogging a review on the gadgets. The
assumption is that actions performed by a user can be seen by their
network friends. Users seeing their friends’ actions are sometimes
tempted to perform those actions. We are interested in the problem of
studying the propagation of such “influence”, and on this basis,
identifying which users are leaders when it comes to setting the trend
for performing various actions. We consider alternative definitions of
leaders based on frequent patterns and develop algorithms for their
efficient discovery. Our definitions are based on observing the way
influence propagates in a time window, as the window is moved in time.
Given a social graph and a table of user actions, our algorithms can
discover leaders of various flavors by making one pass over the actions
table. We run detailed experiments to evaluate the utility and
scalability of our algorithms on real-life data. The results of our
experiments confirm on the one hand, the efficiency of the proposed
algorithm, and on the other hand, the effectiveness and relevance of the
overall framework. To the best of our knowledge, this the first frequent
pattern based approach to social network mining.