Are you curious about your psychological well-being without seeing a psychiatrist? Or are you curious about how to sense psychological well-being status via social media? In reality, psychological well-being is difficult to assess in real time on a large scale. However, the popularity and proliferation of social media make it possible to sense and monitor online users’ psychological well-being in a nonintrusive way.
Led by Prof. ZHU Tingshao from the Institute of Psychology of the Chinese Academy of Sciences, the research team revealed how the machine learning model sense people’s psychological well-being and investigated the predictive power of social media corresponding to ground truth well-being data in a psychological way.
To conduct the study, the research team recruited 1427 participants on Sina Weibo platform based on their self-developed online platform. Participants’ well-being were evaluated using a 6-dimensional questionnaire, including environmental mastery, positive relations with others, autonomy, personal growth, self-acceptance and purpose in life.
Then the participants’ posts on social media were collected, and six different psychological lexicons were used to extract linguistic features of the collected posts. A multi-objective prediction model was then built with the extracted linguistic features as input and psychological well-being as the output. Finally, the team evaluated the machine learning model using a method of assessing psychological questionnaires.
The result showed that the machine learning model performed really well based on using the psychological lexicons (or we can call it domain knowledge). Besides, the model also exhibited great performance on 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 well-being data from the perspective of psychological well-being. The study has positive implications for the use of social media to predict mental health in nonprofessional settings such as self-testing or a large-scale user study.
The study entitled “Sensing Psychological Well-being Using Social Media Language: Prediction Model Development Study” has been published since Jan 31, 2023 in Journal of Medical Internet Research and was funded by the Scientific Foundation of the Institute of Psychology, Chinese Academy of Sciences.
Institute of Psychology Chinese Academy of Sciences
Beijing 100101, China.