Object-level ranking: bringing order to Web objects

By Zaiqing Nie, Yuanzhi Zhang, Ji-rong Wen, Wei-Ying Ma. The Web Conference, 2005

316 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

ClusCite: effective citation recommendation by information network-based clustering (2014, methodology): “Furthermore, poor performance of PopRank shows that using only global authority is not sufficient to conduct good citation recommendation.”
HeteSim: A General Framework for Relevance Measure in Heterogeneous Networks (2013, methodology): “ObjectRank [20] applies authority-based ranking to keyword search in labe ed graphs and PopRank [21] proposes a domain-independent object-level link analysismodel.”
PageRank beyond the Web (2014, background): “For instance, the authors of PopRank [Nie et al., 2005] consider searching through large databases of objects – think of academic papers – that have their own internal set of relationships within the knowledge system – think of co-author relationships.”
Relational retrieval using a combination of path-constrained random walks (2010, methodology): “Nie et al. (2005) use exhaustive local search over each edge type, which is only applicable when the number of parameters is very small.”
PathSim (2011, background): “ObjectRank [1] and PopRank [13] ﬁrst noticed that heterogeneous relationships could affect the random walk, and assigned different propagation factors to each type of object relationship to either derive a revised version of P-PageRank (ObjectRank) or a global PageRank (PopRank).”