Predicting Big Five personality traits from smartphone data: A meta-analysis on the potential of digital phenotyping

On the Willingness to Pay for social media/messenger services taking into account personality and sent/received messages among WhatsApp users

WhatsApp has billions of users worldwide. Instead of paying a subscription fee, users provide their data for the use allowance. This data is used by Meta - the company behind WhatsApp - to obtain insights into user characteristics and monetize those insights. However, this data business model is among others criticized for fostering a loss of privacy that arises when platforms analyze user data, and for the use of design elements to attract users to the platform when they are not online or to extend their online time. Therefore, an increasing number of scientists are discussing whether other payment models are needed to overcome those disadvantages, like a monetary payment model. However, users would probably only pay for improved social media products. This paper provides an empirical basis for understanding the user perspective and, in particular, whether and how much users are willing to pay for improved social media products. For this, 2924 WhatsApp users' perspectives on this topic were investigated. They were asked whether and how much they are willing to pay money for a messenger/social media service when its quality would be improved. Variables potentially influencing Willingness to Pay (i.e., personality, sent/received messages) were studied as well. 47% of the participants were unwilling to pay for a healthier messenger service, and about a quarter were willing or stayed neutral. Further analysis revealed that more agreeable people were more willing to pay. Further: Higher Extraversion was associated with more sent/received messages, but the number of sent/received messages was not linked to Willingness to Pay. The present study shows that many users still are not willing to pay for social media (here messengers), which indicates that the advantages of paying for social media with money instead of with one's own data might need to be better communicated.

ChatDashboard: A Framework to collect, link, and process donated WhatsApp Chat Log Data

In this paper, we present ChatDashboard, a framework for collecting, linking, and processing donated WhatsApp chat log data. The framework consists of the WhatsR R package for parsing, anonymizing, and preprocessing donated WhatsApp chat logs, the ChatDashboard R Shiny web app for uploading, reviewing, and securely donating WhatsApp chat logs, and DashboardTester, an automated script for testing the correct setup of the framework by simulating participants. With ChatDashboard, researchers can set up their own data collections to gather transparently donated WhatsApp chat log data from consenting participants and link them to survey responses. It enables researchers to retrospectively collect highly granular data on interpersonal interactions and communication without building their own tools from scratch. We briefly discuss the advantages of donated WhatsApp chat log data for investigating social relationships and provide a detailed explanation of the ChatDashboard framework. Additionally, we provide a step-by-step guideline in the supplementary materials for researchers to set up their own data donation pipelines.

The EPIDIA4Kids protocol for a digital epidemiology study on brain functioning in children, based on a multimodality biometry tool running on an unmodified tablet

Introduction

Neurodevelopment and related mental disorders (NDDs) are one of the most frequent disabilities among young people. They have complex clinical phenotypes often associated with transnosographic dimensions, such as emotion dysregulation and executive dysfunction, that lead to adverse impacts in personal, social, academic, and occupational functioning. Strong overlap exists then across NDDs phenotypes that are challenging for diagnosis and therapeutic intervention. Recently, digital epidemiology uses the rapidly growing data streams from various devices to advance our understanding of health's and disorders' dynamics, both in individuals and the general population, once coupled with computational science. An alternative transdiagnostic approach using digital epidemiology may thus better help understanding brain functioning and hereby NDDs in the general population.

Objective

The EPIDIA4Kids study aims to propose and evaluate in children, a new transdiagnostic approach for brain functioning examination, combining AI-based multimodality biometry and clinical e-assessments on an unmodified tablet. We will examine this digital epidemiology approach in an ecological context through data-driven methods to characterize cognition, emotion, and behavior, and ultimately the potential of transdiagnostic models of NDDs for children in real-life practice.

Methods and analysis

The EPIDIA4Kids is an uncontrolled open-label study. 786 participants will be recruited and enrolled if eligible: they are (1) aged 7 to 12 years and (2) are French speaker/reader; (3) have no severe intellectual deficiencies. Legal representative and children will complete online demographic, psychosocial and health assessments. During the same visit, children will perform additionally a paper/pencil neuro-assessments followed by a 30-min gamified assessment on a touch-screen tablet. Multi-stream data including questionnaires, video, audio, digit-tracking, will be collected, and the resulting multimodality biometrics will be generated using machine- and deep-learning algorithms. The trial will start in March 2023 and is expected to end by December 2024.

Discussion

We hypothesize that the biometrics and digital biomarkers will be capable of detecting early onset symptoms of neurodevelopment compared to paper-based screening while as or more accessible in real-life practice.