In this paper, we present a novel graph data model to analyze eating habits and physical activities of a large number of persons, aiming at automatically detect groups of users sharing the same lifestyle using Social Network Analysis facilities. We focus our attention on physical activities and dietary habits of users because they often can be correlated to several types of diseases. Indeed, they constitute a real example of feature-rich information network (containing multi-relational and heterogeneous data) that can support different analytics. Furthermore, a novel community detection approach has been exploited to detect groups of users sharing same behaviors/habits within the obtained information network by leveraging nodes’ and edges’ properties. Finally, an extensive experimentation on simulated and real networks has been performed for evaluating the proposed approach in terms of efficiency and effectiveness, outperforming some of the most diffused state-of-the-art approaches (up to 8%).

Community detection over feature-rich information networks: An eHealth case study / Moscato, V.; Sperli', G.. - In: INFORMATION SYSTEMS. - ISSN 0306-4379. - 109:Article n.102092(2022). [10.1016/j.is.2022.102092]

Community detection over feature-rich information networks: An eHealth case study

Moscato V.;Sperli' G.
2022

Abstract

In this paper, we present a novel graph data model to analyze eating habits and physical activities of a large number of persons, aiming at automatically detect groups of users sharing the same lifestyle using Social Network Analysis facilities. We focus our attention on physical activities and dietary habits of users because they often can be correlated to several types of diseases. Indeed, they constitute a real example of feature-rich information network (containing multi-relational and heterogeneous data) that can support different analytics. Furthermore, a novel community detection approach has been exploited to detect groups of users sharing same behaviors/habits within the obtained information network by leveraging nodes’ and edges’ properties. Finally, an extensive experimentation on simulated and real networks has been performed for evaluating the proposed approach in terms of efficiency and effectiveness, outperforming some of the most diffused state-of-the-art approaches (up to 8%).
2022
Community detection over feature-rich information networks: An eHealth case study / Moscato, V.; Sperli', G.. - In: INFORMATION SYSTEMS. - ISSN 0306-4379. - 109:Article n.102092(2022). [10.1016/j.is.2022.102092]
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S030643792200076X-main.pdf

solo utenti autorizzati

Descrizione: pdf paper
Tipologia: Versione Editoriale (PDF)
Licenza: Copyright dell'editore
Dimensione 1.86 MB
Formato Adobe PDF
1.86 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11588/902191
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 3
social impact