The digital revolution has not only transformed how people interact but also altered their relationship with self-image. The widespread availability of editing tools that enhance and refine self-portraits, allowing for an overall reconstruction of the face, has sparked concerns among experts as they promote unrealistic beauty standards. Different types and patterns of use on social networking sites (SNSs) may have varying impacts on users’ psychological well-being, particularly when there is limited awareness of risks and digital skills. A Bayesian networks (BNs) framework is implemented to examine the intricate connections among SNSs usage, selfie-taking/sharing/editing behaviors, the digital self-image, internalizing symptoms, and other psychological aspects. In this setting, data dependence structure is learnt from data allowing for studying how changes in one or more variables propagates to all other variables so that alternative hypothetical scenarios may be explored. This presents an attractive statistical tool that supports the decision-making process regarding regulations on SNSs.
Brombin, C., Di Serio, C., Vicard, P. (2024). Improving digital wellbeing in young adult users: a Bayesian networks approach. In Methodological and Applied Statistics and Demography IV SIS 2024, Short Papers, Contributed Sessions 2. Springer.
Improving digital wellbeing in young adult users: a Bayesian networks approach
Paola Vicard
2024-01-01
Abstract
The digital revolution has not only transformed how people interact but also altered their relationship with self-image. The widespread availability of editing tools that enhance and refine self-portraits, allowing for an overall reconstruction of the face, has sparked concerns among experts as they promote unrealistic beauty standards. Different types and patterns of use on social networking sites (SNSs) may have varying impacts on users’ psychological well-being, particularly when there is limited awareness of risks and digital skills. A Bayesian networks (BNs) framework is implemented to examine the intricate connections among SNSs usage, selfie-taking/sharing/editing behaviors, the digital self-image, internalizing symptoms, and other psychological aspects. In this setting, data dependence structure is learnt from data allowing for studying how changes in one or more variables propagates to all other variables so that alternative hypothetical scenarios may be explored. This presents an attractive statistical tool that supports the decision-making process regarding regulations on SNSs.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.