Classification of content and users in BitTorrent by semi-supervised learning methods
- 1 August 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 23766492,p. 625-630
Abstract
P2P downloads still represent a large portion of today's Internet traffic. More than 100 million users operate BitTorrent and generate more than 30% of the total Internet traffic. Recently, a significant research effort has been done to develop tools for automatic classification of Internet traffic by application. The purpose of the present work is to provide a framework for subclassification of P2P traffic generated by the BitTorrent protocol. The general intuition is that the users with similar interests download similar contents. This intuition can be rigorously formalized with the help of graph based semi-supervised learning approach. We have chosen to work with a PageRank based semi-supervised learning method, which scales well with very large volumes of data. We provide recommendations for the choice of parameters in the PageRank based semi-supervised learning method. In particular, we show that it is advantageous to choose labelled points with large PageRank score.Keywords
This publication has 7 references indexed in Scilit:
- Efficient and principled method for detecting communities in networksPhysical Review E, 2011
- Challenging statistical classification for operational usage2009
- Efficient application identification and the temporal and spatial stability of classification schemaComputer Networks, 2009
- Pagerank based clustering of hypertext document collections2008
- Netlib and NA-Net: Building a Scientific Computing CommunityIEEE Annals of the History of Computing, 2008
- A Machine Learning Approach for Efficient Traffic Classification2007 15th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, 2007
- The webgraph framework I2004