Haridas, M. & Caragea, D.: Exploring Wikipedia and DMoz as Knowledge Bases for Engineering a User Interests Hierarchy for Social Network Applications. In: Meersman, R.; Dillon, T. & Herrero, P. (Hrsg.): On the Move to Meaningful Internet Systems: OTM 2009. Berlin / Heidelberg: Springer, 2009 (Lecture Notes in Computer Science 5871), S. 1238-1245
[Volltext]
The outgrowth of social networks in the recent years has resulted in opportunities for interesting data mining problems, such as interest or friendship recommendations. A global ontology over the interests specified by the users of a social network is essential for accurate recommendations. We propose, evaluate and compare three approaches to engineering a hierarchical ontology over user interests. The proposed approaches make use of two popular knowledge bases, Wikipedia and Directory Mozilla, to extract interest definitions and/or relationships between interests. More precisely, the first approach uses Wikipedia to find interest definitions, the latent semantic analysis technique to measure the similarity between interests based on their definitions, and an agglomerative clustering algorithm to group similar interests into higher level concepts. The second approach uses the Wikipedia Category Graph to extract relationships between interests, while the third approach uses Directory Mozilla to extract relationships between interests. Our results show that the third approach, although the simplest, is the most effective for building a hierarchy over user interests.
@incollection{haridas2009exploring,
author = {Haridas, Mandar and Caragea, Doina},
title = {Exploring Wikipedia and DMoz as Knowledge Bases for Engineering a User Interests Hierarchy for Social Network Applications},
editor = {Meersman, Robert and Dillon, Tharam and Herrero, Pilar},
booktitle = {On the Move to Meaningful Internet Systems: OTM 2009},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
address = {Berlin / Heidelberg},
year = {2009},
volume = {5871},
pages = {1238-1245},
url = {http://dx.doi.org/10.1007/978-3-642-05151-7_35},
doi = {10.1007/978-3-642-05151-7_35},
keywords = {ol_web2.0, dmoz, genta11, taxonomy, methods_concepthierarchy, hierarchy, wordnet, data_wikis},
abstract = {The outgrowth of social networks in the recent years has resulted in opportunities for interesting data mining problems, such as interest or friendship recommendations. A global ontology over the interests specified by the users of a social network is essential for accurate recommendations. We propose, evaluate and compare three approaches to engineering a hierarchical ontology over user interests. The proposed approaches make use of two popular knowledge bases, Wikipedia and Directory Mozilla, to extract interest definitions and/or relationships between interests. More precisely, the first approach uses Wikipedia to find interest definitions, the latent semantic analysis technique to measure the similarity between interests based on their definitions, and an agglomerative clustering algorithm to group similar interests into higher level concepts. The second approach uses the Wikipedia Category Graph to extract relationships between interests, while the third approach uses Directory Mozilla to extract relationships between interests. Our results show that the third approach, although the simplest, is the most effective for building a hierarchy over user interests.}
}