Agent-Based Vector-Label Propagation for Explaining Social Network Structures

Valerio Bellandi, Paolo Ceravolo, Ernesto Damiani, Samira Maghool

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Even though Social Network Analysis is quite helpful in studying the structural properties of interconnected systems, real-world networks reveal much more hidden characteristics from interacting domain-specific features. In this study, we designed an Agent-based Vector-label PRopagation Algorithm (AVPRA), which captures both structural properties and domain-specific features of a given network by assigning vectors of features to constituting agents. Experimental analysis proves that our algorithm is accurate in revealing the structural properties of a network in an explainable fashion. Furthermore, the resulting vector-labels are suitable for downstream machine learning tasks.

Original languageBritish English
Title of host publicationKnowledge Management in Organisations - 16th International Conference, KMO 2022, Proceedings
EditorsLorna Uden, I-Hsien Ting, Birgit Feldmann
PublisherSpringer Science and Business Media Deutschland GmbH
Pages306-317
Number of pages12
ISBN (Print)9783031079191
DOIs
StatePublished - 2022
Event16th International Conference on Knowledge Management in Organisations, KMO 2022 - Hagen, Germany
Duration: 11 Jul 202214 Jul 2022

Publication series

NameCommunications in Computer and Information Science
Volume1593 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference16th International Conference on Knowledge Management in Organisations, KMO 2022
Country/TerritoryGermany
CityHagen
Period11/07/2214/07/22

Keywords

  • Explainability
  • Social network analysis
  • Vector-label propagation

Fingerprint

Dive into the research topics of 'Agent-Based Vector-Label Propagation for Explaining Social Network Structures'. Together they form a unique fingerprint.

Cite this