Description
Data set collect for a project investigating the relationship between spontaneous speech features and psychology in the context of the COVID-19 pandemic and lockdown: personality, wellbeing, coping strategies and affect
Abstract
The COVID-19 pandemic presents unprecedented challenges in all aspects of our lives and will continue to do so for an undetermined period of time. Our study investigates two interrelated research questions. First, how will individuals’ circumstances, psychological and emotional characteristics, personality and life conditions influence their perceived impact of this critical situation? And, second, can these features be detectable through analysis of a person’s voice? In order to address our research questions, we propose a protocol for data collection, which consists of a sociodemographic questionnaire (including lockdown habits and conditions), followed by several fully validated psychological tests. These will measure [1] coping strategies (COPE), [2] anxio-depressive symptomatology (HADS), [3] psychological wellbeing (Ryff), [4] guilt, shame or pride (SSGS), and [5] stable personality traits (IPIP-NEO-60). In order to collect voice data, participants will be prompted to produce a spontaneous narrative about their day, whilst audio is being recorded. Data processing will score the psychological questionnaires and apply signal and speech processing to the voice data (i.e. extraction of acoustic features for analysis through machine learning algorithms). Further data analysis will entail the statistical testing of different hypotheses on a range of relationships between the collected variables, including speech features. Machine learning methods will be employed to characterise the participant’s expression of emotions through speech. In a nutshell, this study aims to compare people with different personality traits on the basis of their coping strategies, wellbeing and certain feelings during the lockdown. This brings about the possibility to design psychological recommendations from a “precision medicine” perspective: that is, recommendations tailored to actual personality traits. In a world that was already pacing towards e-health, now that COVID-19 has forced this pace to a sudden increase, the inclusion of speech features might enhance the applicability of our findings by contributing to the design of embedded technologies. NOTE: there are 107 voice samples and associated transcripts (professionally obtained) available with this dataset. They are not directly downloadable for data protection reasons, but they can be shared upon request with researchers in the EU/EEA//UK who are able to obtain ethical approval for their project.
Data Citation
De la Fuente Garcia, Sofia; Luz, Saturnino. (2023). PsyVoiD - Investigating the relationship between spontaneous speech features and psychology in the context of the COVID-19 pandemic and lockdown: personality, wellbeing, coping strategies and affect, 2020-2021 [dataset]. University of Edinburgh. Clinical Psychology. https://doi.org/10.7488/ds/7532.
Date made available | 24 Oct 2023 |
---|---|
Publisher | Edinburgh DataShare |