Mining bipartite graphs to improve semantic pedophile activity detection

Abstract : Peer-to-peer (P2P) networks are popular to exchange large volumes of data through the Internet. Paedophile activity is a very important topic for our society and some works have recently attempted to gauge the extent of paedophile exchanges on P2P networks. A key issue is to obtain an efficient detection tool, which may decide if a sequence of keywords is related to the topic or not. We propose to use social network analysis in a large dataset from a P2P network to improve a state-of-the-art filter for paedophile queries. We obtain queries and thus combinations of words which are not tagged by the filter but should be. We also perform some experiments to explore if the original four categories of paedophile queries were to be found by topological measures only.
Complete list of metadatas

Cited literature [5 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01211165
Contributor : Lionel Tabourier <>
Submitted on : Saturday, October 3, 2015 - 5:53:00 PM
Last modification on : Friday, January 17, 2020 - 4:19:35 PM
Long-term archiving on: Monday, January 4, 2016 - 10:16:56 AM

File

rcis2014-FournierDanisch (1).p...
Files produced by the author(s)

Identifiers

Citation

Raphaël Fournier, Maximilien Danisch. Mining bipartite graphs to improve semantic pedophile activity detection. 8th IEEE International Conference on Research Challenges in Information Science (RCIS 2014), May 2014, Marrakech, Morocco. ⟨10.1109/RCIS.2014.6861035⟩. ⟨hal-01211165⟩

Share

Metrics

Record views

251

Files downloads

284