Connectivity inferences over the web for the analysis of semantic networks
International Journal of Web Engineering and Technology
GIScience'06 Proceedings of the 4th international conference on Geographic Information Science
Connectivity inferences over the web for the analysis of semantic networks
W2GIS'05 Proceedings of the 5th international conference on Web and Wireless Geographical Information Systems
| Hi-index | 0.00 |
In the last few years, a lot of research has been devotedto developing new techniques for improving therecall and the precision of current web search engines.Few works deal with the interesting problem of identifyingthe communities to which pages belong. Most ofthe previous approaches try to cluster data by means ofspectral techniques or by means of traditional hierarchicalalgorithms. The main problem with these techniquesis that they ignore the relevant fact that web communitiesare social networks with distinctive statistical properties.In this paper we analyze web communities on the basisof the evolution of an initial set of hubs and authoritativepages. The evolution jaw captures the behaviour ofpage authors with respect to the popularity of existingpages for the topics of interest. Assuming such a model,we have found interesting properties of web communitiesand we have proposed a technique for computingrelevant properties for specific topics. Several experimentshave confirmed the validity of both the modeland the identification method.