Link Mining: A Survey Lise Getoor and Christopher P. Diehl   View Paper (PDF)   Return to December 2005, Volume 7, Issue 2 Abstract Many datasets of interest today are best described as a linked collection of interrelated ob jects. These may repre- sent homogeneous networks, in which there is a single-ob ject type and link type, or richer, heterogeneous networks, in which there may be multiple ob ject and link types (and possibly other semantic information). Examples of homo- geneous networks include single mode social networks, such as people connected by friendship links, or the WWW, a collection of linked web pages. Examples of heterogeneous networks include those in medical domains describing pa- tients, diseases, treatments and contacts, or in bibliographic domains describing publications, authors, and venues. Link mining refers to data mining techniques that explicitly con- sider these links when building predictive or descriptive mod- els of the linked data. Commonly addressed link mining tasks include ob ject ranking, group detection, collective clas- sification, link prediction and subgraph discovery. While network analysis has been studied in depth in particular ar- eas such as social network analysis, hypertext mining, and web analysis, only recently has there been a cross-fertilization of ideas among these different communities. This is an ex- citing, rapidly expanding area. In this article, we review some of the common emerging themes. ©2006 Association for Computing Machinery