Preference-Based Top-K Influential Nodes Mining in Social Networks

Finding top-K influential nodes in social networks has many important applications. Previous work only considered that one node in the network can influence other nodes with a uniform probability, which doesn´t take user preferences into account and greatly affects the accuracy of results. We propose a two-stage mining algorithm (GAUP) for mining most influential nodes on a specific topic. In the first stage, GAUP uses a collaborative filtering technique to determine user preferences on a topic. Then in the second stage, GAUP adopts a greedy algorithm to find top-K nodes in the network. Our evaluation shows that our GAUP algorithm can successfully mine top nodes for a given topic.