In this paper, we present algorithms for ranking nodes in interaction networks. Informally,
they capture the patterns of historical interaction among the nodes and the associated out-
comes. There exists a cardinal ranking over the set of outcomes, characterizing the order of
preference. We argue that ranking of nodes should be influenced by both structural proper-
ties of the networks and the outcome/value created by the interactions. The former aspect is
well studied in social network analysis and is accounted for, in various measures like centrality,
reputation, influence etc. However, the latter aspect is largely unexplored. Our proposed algo-
rithms simultaneously take into account both structural properties as well as the outcomes to
assign ranks for the nodes. We develop a novel eigenvector-like computation that exploits the
structural influences, importance of value creation, and any exogenous information available to
the ranking system. We report experimental results on the IMDB dataset.
By: Kashyap Dixit, S Kameshwaran, Sameep Mehta, Vinayaka Pandit and N Viswanadham
Published in: RI09002 in 2009
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .