Characterizing daily social context using personal smartphone Bluetooth logs and digital communication metadata

Incorporating engineered features of day-to-day, in-person and online social exposure from IoT data to improve health sensing predictive performance.

Status of this project: on the back burner, but collaborators welcome.


  • Wu, C., Barczyk, A. N., Craddock, R. C., Harari, G. M., Thomaz, E., Shumake, J. D., … & Schnyer, D. M. (2021). Improving prediction of real-time loneliness and companionship type using geosocial features of personal smartphone data. Smart Health20, 100180.
  • Wu, C., Boukhechba, M., Cai, L., Barnes, L. E., & Gerber, M. S. (2018). Improving momentary stress measurement and prediction with bluetooth encounter networks. Smart Health9, 219-231.
  • Wu, C., Cai, L., Gerber, M. S., Boukhechba, M., & Barnes, L. E. (2018, October). Vector space representation of bluetooth encounters for mental health inference. In Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers (pp. 1691-1699).
  • Mendu, S., Baglione, A., Baee, S., Wu, C., Ng, B., Shaked, A., … & Barnes, L. (2020). A framework for understanding the relationship between social media discourse and mental health. Proceedings of the ACM on Human-Computer Interaction4(CSCW2), 1-23.
  • Mendu, S., Boukhechba, M., Baglione, A., Baee, S., Wu, C., & Barnes, L. (2019, January). SocialText: A framework for understanding the relationship between digital communication patterns and mental health. In 2019 IEEE 13th international conference on semantic computing (ICSC) (pp. 428-433). IEEE.