Difference between revisions of "Exploratory Recommendations Using Wikipedia's Linking Structure"
(Adding wikilinks) |
(Infobox) |
||
Line 1: | Line 1: | ||
+ | {{Infobox work | ||
+ | | title = Exploratory Recommendations Using Wikipedia's Linking Structure | ||
+ | | date = 2011 | ||
+ | | authors = [[Adrian M. Kentsch]]<br />[[Walter A. Kosters]]<br />[[Peter van der Putten]]<br />[[Frank W. Takes]] | ||
+ | | link = http://liacs.leidenuniv.nl/~takesfw/pdf/kentschbenelearn.pdf | ||
+ | }} | ||
'''Exploratory Recommendations Using Wikipedia's Linking Structure''' - scientific work related to [[Wikipedia quality]] published in 2011, written by [[Adrian M. Kentsch]], [[Walter A. Kosters]], [[Peter van der Putten]] and [[Frank W. Takes]]. | '''Exploratory Recommendations Using Wikipedia's Linking Structure''' - scientific work related to [[Wikipedia quality]] published in 2011, written by [[Adrian M. Kentsch]], [[Walter A. Kosters]], [[Peter van der Putten]] and [[Frank W. Takes]]. | ||
== Overview == | == Overview == | ||
This ongoing research addresses the use of page ranking for computing [[relatedness]] coefcients between pairs of nodes in a directed graph, based on their edge structure. A novel, hybrid algorithm is proposed for a complete assessment of nodes and their connecting edges, which is then applied to a practical application, namely a recommender system for books, authors, and their respective movie adaptations. Through relatedness, a level of surprise can be added to the recommender. The recommendation is created by exploring and discovering items of interest beyond the scope of books and authors. These items are then used in an explanatory manner to support the resulting recommendation. The chosen knowledge base is [[Wikipedia]], a suitable source for both computing relatedness coecients and applying them to the specic recommender system for reading material. | This ongoing research addresses the use of page ranking for computing [[relatedness]] coefcients between pairs of nodes in a directed graph, based on their edge structure. A novel, hybrid algorithm is proposed for a complete assessment of nodes and their connecting edges, which is then applied to a practical application, namely a recommender system for books, authors, and their respective movie adaptations. Through relatedness, a level of surprise can be added to the recommender. The recommendation is created by exploring and discovering items of interest beyond the scope of books and authors. These items are then used in an explanatory manner to support the resulting recommendation. The chosen knowledge base is [[Wikipedia]], a suitable source for both computing relatedness coecients and applying them to the specic recommender system for reading material. |
Revision as of 11:46, 20 June 2019
Authors | Adrian M. Kentsch Walter A. Kosters Peter van der Putten Frank W. Takes |
---|---|
Publication date | 2011 |
Links | Original |
Exploratory Recommendations Using Wikipedia's Linking Structure - scientific work related to Wikipedia quality published in 2011, written by Adrian M. Kentsch, Walter A. Kosters, Peter van der Putten and Frank W. Takes.
Overview
This ongoing research addresses the use of page ranking for computing relatedness coefcients between pairs of nodes in a directed graph, based on their edge structure. A novel, hybrid algorithm is proposed for a complete assessment of nodes and their connecting edges, which is then applied to a practical application, namely a recommender system for books, authors, and their respective movie adaptations. Through relatedness, a level of surprise can be added to the recommender. The recommendation is created by exploring and discovering items of interest beyond the scope of books and authors. These items are then used in an explanatory manner to support the resulting recommendation. The chosen knowledge base is Wikipedia, a suitable source for both computing relatedness coecients and applying them to the specic recommender system for reading material.