V
Vincent Labatut
Researcher at University of Avignon
Publications - 125
Citations - 1807
Vincent Labatut is an academic researcher from University of Avignon. The author has contributed to research in topics: Complex network & Context (language use). The author has an hindex of 23, co-authored 114 publications receiving 1558 citations. Previous affiliations of Vincent Labatut include French Institute of Health and Medical Research & Galatasaray University.
Papers
More filters
Journal ArticleDOI
Comparative evaluation of community detection algorithms: a topological approach
TL;DR: In this paper, a comprehensive comparative study of a representative set of community detection methods is presented, in which community-oriented topological measures are used to qualify the communities and evaluate their deviation from the reference structure.
Journal ArticleDOI
Comparative Evaluation of Community Detection Algorithms: A Topological Approach
TL;DR: A comprehensive comparative study of a representative set of community detection methods, in which community-oriented topological measures are used to qualify the communities and evaluate their deviation from the reference structure and it turns out there is no equivalence between the two approaches.
Book ChapterDOI
A Comparison of Community Detection Algorithms on Artificial Networks
TL;DR: This work uses Lancichinetti et al. model, which is able to generate networks with controlled power-law degree and community distributions, to test some community detection algorithms and uses the normalized mutual information measure to assess the quality of the results and compare the considered algorithms.
Posted Content
Accuracy Measures for the Comparison of Classifiers
Vincent Labatut,Hocine Cherifi +1 more
TL;DR: This work focuses on the measure used to assess the classification performance and rank the algorithms, and presents the most popular measures and discusses their properties.
Book ChapterDOI
Qualitative Comparison of Community Detection Algorithms
TL;DR: This study generates networks thanks to the most realistic model available to date and applies five community detection algorithms on these networks, finding out the performance assessed quantitatively does not necessarily agree with a qualitative analysis of the identified communities.