Conceptual and statistical footprints for social networks' characterization

Authors:
Trad Mohamed Riadh;Bénédicte Le Grand;Marie-Aude Aufaure;Michel Soto
Affiliations:
Laboratoire MAS, Ecole Centrale Paris;Laboratoire d'Informatique de Paris - UPMC;Laboratoire MAS, Ecole Centrale Paris;Laboratoire d'Informatique de Paris - UPMC
Venue:
Proceedings of the 3rd Workshop on Social Network Mining and Analysis
Year:
2009

Citing 2
Cited 1

Social information access: the other side of the social web

SOFSEM'08 Proceedings of the 34th conference on Current trends in theory and practice of computer science
Analysis of social communities with iceberg and stability-based concept lattices

ICFCA'08 Proceedings of the 6th international conference on Formal concept analysis

Applying the JBOS reduction method for relevant knowledge extraction

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article proposes a method relying on Formal Concept Analysis and Galois lattices for complex systems analysis. Statistics based on concept lattices enable the computation of the "Conceptual Distribution" of objects classified by the lattice. Experimentation on sample datasets extracted from three online social networks illustrates the use of these conceptual statistics for the global characterization and the automatic filtering of these systems. Moreover, compared to classical measures, these statistics offer new perspectives for object filtering and lattices simplification that would be useful for lattices visualization and interpretation. However, conceptual statistics calculation, based on Galois lattices computation requires expensive calculations. This paper focuses on conceptual statistics contribution and optimized methods for their calculation for scalability purposes.