Telecommunication networks: protocols, modeling and analysis
Telecommunication networks: protocols, modeling and analysis
On power-law relationships of the Internet topology
Proceedings of the conference on Applications, technologies, architectures, and protocols for computer communication
Communication motifs: a tool to characterize social communications
CIKM '10 Proceedings of the 19th ACM international conference on Information and knowledge management
Hi-index | 0.00 |
This paper addresses the problem of predicting several attributes corresponding to telephone users, based on information gathered from the network which defines their communication patterns. Two approaches are compared which are grounded on machine learning techniques: the initial approach makes use of link information between two users, looking for the correlation between user attributes and communication patterns. The second approach exploits the network structure underlying the communication behavior of the user under study. Simulations show that the learning machines are able to extract network information to improve the attribute prediction capabilities.