Normalized values: (A) environmental mastery, (B) positive relationships, (C) autonomy item, (D) personal growth, (E) self-acceptance, (F) purpose in life. Credit: Journal of Medical Internet Research (2023). DOI: 10.2196/41823
Curious about your mental wellbeing without seeing a psychiatrist? Or are you curious about how you can get a sense of your mental well-being through social media? In reality, large-scale mental well-being is difficult to assess in real time. However, the popularity and proliferation of social media makes it possible to measure and monitor the psychological well-being of online users in a non-intrusive way.
A research team led by Prof. Zhu Tingshao from the Institute of Psychology of the Chinese Academy of Sciences (CAS) demonstrated how a machine learning model captures people’s mental well-being and examined the predictive power of social media, which corresponds to the good truth. to be data in a psychological way. The study, titled “Sensing Psychological Well-being Using Social Media Language: Prediction Model Development Study,” was published Jan. 31 in the Journal of Medical Internet Research.
On the Sina Weibo platform, the researchers recruited 1,427 participants based on their self-developed online platform. Participant well-being was assessed using a 6-dimensional questionnaire, including environmental mastery, positive relationships with others, autonomy, personal growth, self-acceptance, and purpose in life.
Participants’ social media posts were then collected and six different psychological lexicons were used to extract linguistic features from the collected posts. A multi-objective predictive model was then built using the extracted linguistic features as input and psychological well-being as output.
Finally, they evaluated the machine learning model using a psychological questionnaire scoring method.
The result showed that the machine learning model based on the use of psychological lexicons performs very well. In addition, the model also showed excellent performance in terms of reliability and validity.
By confirming the reliability and validity of the machine learning prediction model, the study verified the predictability of social media corresponding to ground truth wellbeing data from a psychological wellbeing perspective. The study has positive implications for using social media to predict mental health in non-professional settings such as self-testing or a large-scale user study.
For more information, see Nuo Han et al., Sensing Psychological Well-being Using Social Media Language: Prediction Model Development Study, Journal of Medical Internet Research (2023). DOI: 10.2196/41823
Provided by the Chinese Academy of Sciences
Citation: Scientists Show Validity of Using Social Media to Predict User’s Psychological Well-Being (2023 March 8) Retrieved March 8, 2023 from https://medicalxpress.com/news/2023-03-scientists-validity- social-media-user.html
This document is protected by copyright. Except for fair trade for the purpose of private study or research, no part may be reproduced without written permission. The content is for informational purposes only.
