Show simple item record

dc.contributor.authorDai, Sicheng
dc.contributor.authorBouchet, Hélène
dc.contributor.authorNardy, Aurélie
dc.contributor.authorFleury, Eric
dc.contributor.authorChevrot, Jean-Pierre
dc.contributor.authorKarsai, Márton
dc.date.accessioned2023-06-16T14:43:13Z
dc.date.available2023-06-16T14:43:13Z
dc.date.issued2020
dc.identifier.issn2193-1127
dc.identifier.doi10.1140/epjds/s13688-020-00237-8
dc.identifier.urihttp://hdl.handle.net/20.500.14018/13855
dc.description.abstractThe emerging technologies of wearable wireless devices open entirely new ways to record various aspects of human social interactions in a broad range of settings. Such technologies allow to log the temporal dynamics of face-to-face interactions by detecting the physical proximity of participants. However, despite the wide usage of this technology and the collected datasets, precise reconstruction methods transforming the raw recorded communication data packets to social interactions are still missing. In this study we analyse a proximity dataset collected during a longitudinal social experiment aiming to understand the co-evolution of children’s language development and social network. Physical proximity and verbal communication of hundreds of pre-school children and their teachers are recorded over three years using autonomous wearable low power wireless devices. The dataset is accompanied with three annotated ground truth datasets, which record the time, distance, relative orientation, and interaction state of interacting children for validation purposes. We use this dataset to explore several pipelines of dynamical event reconstruction including earlier applied naïve approaches, methods based on Hidden Markov Model, or on Long Short-Term Memory models, some of them combined with supervised pre-classification of interaction packets. We find that while naïve models propose the worst reconstruction, Long Short-Term Memory models provide the most precise way to reconstruct real interactions up to ${\sim} 90\%$∼90% accuracy. Finally, we simulate information spreading on the reconstructed networks obtained by the different methods. Results indicate that small improvement of network reconstruction accuracy may lead to significantly different spreading dynamics, while sometimes large differences in accuracy have no obvious effects on the dynamics. This not only demonstrates the importance of precise network reconstruction but also the careful choice of the reconstruction method in relation with the data collected. Missing this initial step in any study may seriously mislead conclusions made about the emerging properties of the observed network or any dynamical process simulated on it.
dc.language.isoeng
dc.publisherSpringer
dc.rightsCC BY 4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectPhysical proximity networks
dc.subjectTemporal network reconstruction
dc.subjectSupervised learning
dc.subjectData-driven modelling of spreading processes
dc.titleTemporal social network reconstruction using wireless proximity sensors: model selection and consequences
dc.typeJournal article
dc.source.journaltitleEPJ Data Science
dc.source.volume9
dc.source.issue1
dc.source.spage1
dc.source.epage21
dc.description.versionPublished version
refterms.dateFOA2023-06-16T14:43:13Z
dc.contributor.unitDepartment of Network and Data Science
dc.source.journalabbrevEPJ Data Sci.
dc.identifier.urlhttps://epjdatascience.springeropen.com/articles/10.1140/epjds/s13688-020-00237-8


Files in this item

Thumbnail
Name:
Dai-Sicheng_2020.pdf
Size:
2.408Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

CC BY 4.0
Except where otherwise noted, this item's license is described as CC BY 4.0