Information Technology Reference
In-Depth Information
Ranking Learning Entities on the Web by
Integrating Network-Based Features
Yingzi Jin, Yutaka Matsuo, and Mitsuru Ishizuka
Abstract.
Many efforts are undertaken by people and companies to improve their
popularity, growth, and power, the outcomes of which are all expressed as rank-
ings (designated as target rankings). Are these rankings merely the results of those
person's or that company's own attributes? In the theory of social network analy-
sis (SNA), the performance and power of actors are usually interpreted as relations
and the relational structures in which they are embedded. We propose an algorithm
to generate and integrate network-based features systematically from a given social
network that is mined from the world-wide web. After learning a model for explain-
ing target rankings researchers' productivity based on social networks confirms the
effectiveness of our models. This chapter specifically examines the application of a
social network that exemplifies the advanced use of social networks mined from the
web.
1
Introduction
People prefer to use rankings to compare companies, to discuss elections, and to
evaluate goods. For example, investors seek to invest their funds in fast-growing and
stable companies; consumers tend to buy highly popular products. Therefore, many
