Link analysis methods are used to estimate importance in graph-structured data. In that realm, the PageRank algorithm has been used to analyze directed graphs, in particular the link structure of the Web. Recent developments in information retrieval focus on entities and their relations (i.e., knowledge graph panels). Many entities are documented in the popular knowledge base Wikipedia. The cross-references within Wikipedia exhibit a directed graph structure that is suitable for computing PageRank scores as importance indicators for entities. In this work, we present different PageRank-based analyses on the link graph of Wikipedia and according experiments. We focus on the question whether some links—based on their context/position in the article text—can be deemed more important than others. In our variants, we change the probabilistic impact of links in accordance to their context/position on the page and measure the effects on the output of the PageRank algorithm. We compare the resulting rankings and those of existing systems with page-view-based rankings and provide statistics on the pairwise computed Spearman and Kendall rank correlations.
%0 Book Section
%1 thalhammer2016pagerank
%A Thalhammer, Andreas
%A Rettinger, Achim
%B The Semantic Web: ESWC 2016 Satellite Events, Heraklion, Crete, Greece, May 29 -- June 2, 2016, Revised Selected Papers
%D 2016
%E Sack, Harald
%E Rizzo, Giuseppe
%E Steinmetz, Nadine
%E Mladenić, Dunja
%E Auer, Sören
%E Lange, Christoph
%I Springer
%K dbpedia entity importance pagerank ranking score wikidata wikipedia
%P 227--240
%R 10.1007/978-3-319-47602-5_41
%T PageRank on Wikipedia: Towards General Importance Scores for Entities
%U http://dx.doi.org/10.1007/978-3-319-47602-5_41
%X Link analysis methods are used to estimate importance in graph-structured data. In that realm, the PageRank algorithm has been used to analyze directed graphs, in particular the link structure of the Web. Recent developments in information retrieval focus on entities and their relations (i.e., knowledge graph panels). Many entities are documented in the popular knowledge base Wikipedia. The cross-references within Wikipedia exhibit a directed graph structure that is suitable for computing PageRank scores as importance indicators for entities. In this work, we present different PageRank-based analyses on the link graph of Wikipedia and according experiments. We focus on the question whether some links—based on their context/position in the article text—can be deemed more important than others. In our variants, we change the probabilistic impact of links in accordance to their context/position on the page and measure the effects on the output of the PageRank algorithm. We compare the resulting rankings and those of existing systems with page-view-based rankings and provide statistics on the pairwise computed Spearman and Kendall rank correlations.
%@ 978-3-319-47602-5
@inbook{thalhammer2016pagerank,
abstract = {Link analysis methods are used to estimate importance in graph-structured data. In that realm, the PageRank algorithm has been used to analyze directed graphs, in particular the link structure of the Web. Recent developments in information retrieval focus on entities and their relations (i.e., knowledge graph panels). Many entities are documented in the popular knowledge base Wikipedia. The cross-references within Wikipedia exhibit a directed graph structure that is suitable for computing PageRank scores as importance indicators for entities. In this work, we present different PageRank-based analyses on the link graph of Wikipedia and according experiments. We focus on the question whether some links—based on their context/position in the article text—can be deemed more important than others. In our variants, we change the probabilistic impact of links in accordance to their context/position on the page and measure the effects on the output of the PageRank algorithm. We compare the resulting rankings and those of existing systems with page-view-based rankings and provide statistics on the pairwise computed Spearman and Kendall rank correlations.},
added-at = {2016-12-23T17:41:08.000+0100},
author = {Thalhammer, Andreas and Rettinger, Achim},
biburl = {https://www.bibsonomy.org/bibtex/29b3f72885c1b9c160df607567ecd9f29/jaeschke},
booktitle = {The Semantic Web: ESWC 2016 Satellite Events, Heraklion, Crete, Greece, May 29 -- June 2, 2016, Revised Selected Papers},
doi = {10.1007/978-3-319-47602-5_41},
editor = {Sack, Harald and Rizzo, Giuseppe and Steinmetz, Nadine and Mladeni{\'{c}}, Dunja and Auer, S{\"o}ren and Lange, Christoph},
interhash = {1ba1470bb7b2d0683b46bfa866a54ada},
intrahash = {9b3f72885c1b9c160df607567ecd9f29},
isbn = {978-3-319-47602-5},
keywords = {dbpedia entity importance pagerank ranking score wikidata wikipedia},
pages = {227--240},
publisher = {Springer},
timestamp = {2016-12-23T17:41:08.000+0100},
title = {PageRank on Wikipedia: Towards General Importance Scores for Entities},
url = {http://dx.doi.org/10.1007/978-3-319-47602-5_41},
year = 2016
}