# Watch your Watch: Inferring Personality Traits from Wearable Activity Trackers
**Source**: https://iris.unil.ch/entities/publication/2f0bffef-3752-4624-a942-ebba806fa5e3
**Parent**: https://wp.unil.ch/hecoutreach/connected-watches-and-privacy-risks-dangers-and-data-protection/
Titre
# Watch your Watch: Inferring Personality Traits from Wearable Activity Trackers
Type
article de conférence/colloque
Institution
UNIL/CHUV/Unisanté + institutions partenaires
Auteur(s)
Zufferey, Noé
Auteure/Auteur
Humbert, Mathias
Auteure/Auteur
Tavenard, Romain
Auteure/Auteur
Huguenin, Kévin
Auteure/Auteur
Liens vers les personnes
[Huguenin, Kévin](https://iris.unil.ch/entities/person/2944935d-0b87-49be-9948-63cc91c050ff)
[Zufferey, Noé](https://iris.unil.ch/entities/person/00ac6ba8-e370-4508-ba04-e3b846b40c81)
[Humbert, Mathias](https://iris.unil.ch/entities/person/b2c29137-b436-4bb5-ac26-179cfdf81053)
Liens vers les unités
[Département des systèmes d'information](https://iris.unil.ch/entities/orgunit/ea5cb1db-0d46-435a-9f5e-e334d1b6ec0e)
Maison d’édition
USENIX
Titre du livre ou conférence/colloque
Proceedings of the USENIX Security Symposium (USENIX Security)
Adresse
Anaheim, CA, United States
Statut éditorial
Publié
Date de publication
2023-08
Première page
18
Peer-reviewed
Oui
Langue
anglais
Résumé
Wearable devices, such as wearable activity trackers (WATs), are increasing in popularity. Although they can help to improve one’s quality of life, they also raise serious privacy issues. One particularly sensitive type of information has recently attracted substantial attention, namely personality; as personality provides a means to influence individuals (e.g., voters in the Cambridge Analytica scandal). This paper presents the first empirical study to show a significant correlation between WAT data and personality traits (Big Five). We conduct an experiment with 200+ participants. The ground truth was established by using the NEO-PI-3 questionnaire. The participants’ step count, heart rate, battery level, activities, sleep time, etc. were collected for four months. By following a principled machine-learning approach, the participants’ personality privacy was quantified. Our results demonstrate that WATs data brings valuable information to infer the openness, extraversion, and neuroticism personality traits. We further study the importance of the different features (i.e., data types) and found that step counts play a key role in the inference of extraversion and neuroticism, while openness is more related to heart rate.
PID Serval
serval:BIB\_4312C7E1B88F
Permalien
<https://iris.unil.ch/handle/iris/116693>
URL éditeur
<https://www.usenix.org/conference/usenixsecurity23/presentation/zufferey>
DOI données de recherche
10.5281/zenodo.7621224
Open Access
Oui
Date de création
2023-02-23T21:08:21.251Z
Date de création dans IRIS
2025-05-20T19:48:14Z
Fichier(s)
En cours de chargement...
Télécharger
**Nom**
Zufferey2023USENIX.pdf
**Version du manuscrit**
postprint
**Visibilité**
Accès ouvert
**Taille**
423.69 KB
**Format**
Adobe PDF
**PID Serval**
serval:BIB\_4312C7E1B88F.P001
**URN**
[urn:nbn:ch:serval-BIB\_4312C7E1B88F0](https://nbn-resolving.org/urn:nbn:ch:serval-BIB_4312C7E1B88F0)
**Somme de contrôle**
(MD5):24972bf86ed9419bf6e4e40d7035141d