The Mobile Phone Use Dataset contains mobile phone use logs of 342 study participants. The data was collected over the course of several weeks during summer 2016.
Download: zip (310 MB)
The archive contain one .csv file per participant. Each .csv file contains events from 25 physical and virtual sensors (e.g. app in foreground, received notifications, ambient noise level, semantic location, ...), frequent self reports of emotions (valence and arousal), and for some participants self-reported traits (Big 5 Traits, Boredom Proneness, Patient Health Questionnaire).
The dataset has been anonymised, i.e., all identifying information has been removed.
If you use this dataset, please cite the following publication is its source:
Beyond Interruptibility: Predicting Opportune Moments to Engage Mobile Phone Users. Martin Pielot, Bruno Cardoso, Kleomenis Katevas, Joan Serrà, Aleksandar Matic, Nuria Oliver. UbiComp ’17: ACM International Joint Conference on Pervasive and Ubiquitous Computing, 2017.
Please note, the original non-anomymized dataset and the analysis scripts used for publications are the intellectual property of my former employer, Telefónica. I do no longer have access to either of those. Only the anonymized dataset was released to the public via Crawdad.
If you are looking for scripts that can help getting started with analysing the data, please check out this GitHub repository https://github.com/minoskt/mpu-feature-extraction