Inference of demographic attributes based on mobile phone usage patterns and social network topology

Mobile phone usage provides a wealth of information, which can be used to better understand the demographic structure of a population. In this paper, we focus on the population of Mexican mobile phone users. We first present an observational study of mobile phone usage according to gender and age gr...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Sarraute, C., Brea, J., Burroni, J., Blanc, P.
Formato: JOUR
Materias:
Call detail records
Demographics
Graph mining
Homophily
Mobile phone social network
Social network analysis
Cellular telephones
Learning systems
Mobile phones
Mobile telecommunication systems
Population statistics
Telephone sets
Topology
Communication graphs
Demographic features
Topological relations
Wealth of information
Social networking (online)
Acceso en línea:http://hdl.handle.net/20.500.12110/paper_18695450_v5_n1_p1_Sarraute
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
id todo:paper_18695450_v5_n1_p1_Sarraute
record_format dspace
spelling todo:paper_18695450_v5_n1_p1_Sarraute2023-10-03T16:33:51Z Inference of demographic attributes based on mobile phone usage patterns and social network topology Sarraute, C. Brea, J. Burroni, J. Blanc, P. Call detail records Demographics Graph mining Homophily Mobile phone social network Social network analysis Cellular telephones Learning systems Mobile phones Mobile telecommunication systems Population statistics Telephone sets Topology Call detail records Communication graphs Demographic features Demographics Graph mining Homophily Topological relations Wealth of information Social networking (online) Mobile phone usage provides a wealth of information, which can be used to better understand the demographic structure of a population. In this paper, we focus on the population of Mexican mobile phone users. We first present an observational study of mobile phone usage according to gender and age groups. We are able to detect significant differences in phone usage among different subgroups of the population. We then study the performance of different machine learning (ML) methods to predict demographic features (namely, age and gender) of unlabeled users by leveraging individual calling patterns, as well as the structure of the communication graph. We show how a specific implementation of a diffusion model, harnessing the graph structure, has significantly better performance over other node-based standard ML methods. We provide details of the methodology together with an analysis of the robustness of our results to changes in the model parameters. Furthermore, by carefully examining the topological relations of the training nodes (seed nodes) to the rest of the nodes in the network, we find topological metrics which have a direct influence on the performance of the algorithm. © 2015, Springer-Verlag Wien. JOUR info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_18695450_v5_n1_p1_Sarraute
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-134
collection Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic Call detail records
Demographics
Graph mining
Homophily
Mobile phone social network
Social network analysis
Cellular telephones
Learning systems
Mobile phones
Mobile telecommunication systems
Population statistics
Telephone sets
Topology
Call detail records
Communication graphs
Demographic features
Demographics
Graph mining
Homophily
Topological relations
Wealth of information
Social networking (online)
spellingShingle Call detail records
Demographics
Graph mining
Homophily
Mobile phone social network
Social network analysis
Cellular telephones
Learning systems
Mobile phones
Mobile telecommunication systems
Population statistics
Telephone sets
Topology
Call detail records
Communication graphs
Demographic features
Demographics
Graph mining
Homophily
Topological relations
Wealth of information
Social networking (online)
Sarraute, C.
Brea, J.
Burroni, J.
Blanc, P.
Inference of demographic attributes based on mobile phone usage patterns and social network topology
topic_facet Call detail records
Demographics
Graph mining
Homophily
Mobile phone social network
Social network analysis
Cellular telephones
Learning systems
Mobile phones
Mobile telecommunication systems
Population statistics
Telephone sets
Topology
Call detail records
Communication graphs
Demographic features
Demographics
Graph mining
Homophily
Topological relations
Wealth of information
Social networking (online)
description Mobile phone usage provides a wealth of information, which can be used to better understand the demographic structure of a population. In this paper, we focus on the population of Mexican mobile phone users. We first present an observational study of mobile phone usage according to gender and age groups. We are able to detect significant differences in phone usage among different subgroups of the population. We then study the performance of different machine learning (ML) methods to predict demographic features (namely, age and gender) of unlabeled users by leveraging individual calling patterns, as well as the structure of the communication graph. We show how a specific implementation of a diffusion model, harnessing the graph structure, has significantly better performance over other node-based standard ML methods. We provide details of the methodology together with an analysis of the robustness of our results to changes in the model parameters. Furthermore, by carefully examining the topological relations of the training nodes (seed nodes) to the rest of the nodes in the network, we find topological metrics which have a direct influence on the performance of the algorithm. © 2015, Springer-Verlag Wien.
format JOUR
author Sarraute, C.
Brea, J.
Burroni, J.
Blanc, P.
author_facet Sarraute, C.
Brea, J.
Burroni, J.
Blanc, P.
author_sort Sarraute, C.
title Inference of demographic attributes based on mobile phone usage patterns and social network topology
title_short Inference of demographic attributes based on mobile phone usage patterns and social network topology
title_full Inference of demographic attributes based on mobile phone usage patterns and social network topology
title_fullStr Inference of demographic attributes based on mobile phone usage patterns and social network topology
title_full_unstemmed Inference of demographic attributes based on mobile phone usage patterns and social network topology
title_sort inference of demographic attributes based on mobile phone usage patterns and social network topology
url http://hdl.handle.net/20.500.12110/paper_18695450_v5_n1_p1_Sarraute
work_keys_str_mv AT sarrautec inferenceofdemographicattributesbasedonmobilephoneusagepatternsandsocialnetworktopology
AT breaj inferenceofdemographicattributesbasedonmobilephoneusagepatternsandsocialnetworktopology
AT burronij inferenceofdemographicattributesbasedonmobilephoneusagepatternsandsocialnetworktopology
AT blancp inferenceofdemographicattributesbasedonmobilephoneusagepatternsandsocialnetworktopology
_version_ 1807321563548090368

Ejemplares similares