Journal of affective disorders · 2025
Identifying possible influence factors for depression through social media.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Wang Ruijuan, Ji Ziqing, Chen Yining, Wu Hengchang, Liang Xiaohui
Аннотация
BACKGROUND: Nowadays, social media provide a wealth of real-time data on emotional expression. This paper aims to explore possible influence factors for depression using internet-based data, thereby contributing references for psychological research and future depression intervention.
METHODS: Posts under Weibo named "Zoufan" were crawled and manually annotated. Depression levels, personality traits and external factors reflected from these texts were classified by BERT model. Single factor analysis and unordered multinomial logistic regression analysis were conducted for the relationship between depression and possible influence factors. Random forest analysis was applied to evaluate the significance these factors.
RESULTS: The final dataset included 50,306 users. Among personality traits, high extraversion and agreeableness were found to be protective factors against depression (p < 0.01), while high neuroticism was identified as a significant risk factor (p < 0.01). Concerning external factors, family-related issues increased the risk of extreme depression (p < 0.01), while romantic relationships were associated with mild (p < 0.01) and moderate depression (p < 0.05). Furthermore, interpersonal relationship challenges were linked to an elevated risk of mild, moderate, and severe depression (p < 0.01). Factors such as love, family, and interpersonal relationships reflect the role of social support, which is crucial in preventing depression.
CONCLUSION: High extraversion and agreeableness reduce the likelihood of depression, while high neuroticism increases the risk. A supportive social environment plays a vital role in depression. Moreover, utilizing big data from social media extends beyond traditional questionnaire-based methods, offering novel perspectives and pathways for mental health research and interventions.
METHODS: Posts under Weibo named "Zoufan" were crawled and manually annotated. Depression levels, personality traits and external factors reflected from these texts were classified by BERT model. Single factor analysis and unordered multinomial logistic regression analysis were conducted for the relationship between depression and possible influence factors. Random forest analysis was applied to evaluate the significance these factors.
RESULTS: The final dataset included 50,306 users. Among personality traits, high extraversion and agreeableness were found to be protective factors against depression (p < 0.01), while high neuroticism was identified as a significant risk factor (p < 0.01). Concerning external factors, family-related issues increased the risk of extreme depression (p < 0.01), while romantic relationships were associated with mild (p < 0.01) and moderate depression (p < 0.05). Furthermore, interpersonal relationship challenges were linked to an elevated risk of mild, moderate, and severe depression (p < 0.01). Factors such as love, family, and interpersonal relationships reflect the role of social support, which is crucial in preventing depression.
CONCLUSION: High extraversion and agreeableness reduce the likelihood of depression, while high neuroticism increases the risk. A supportive social environment plays a vital role in depression. Moreover, utilizing big data from social media extends beyond traditional questionnaire-based methods, offering novel perspectives and pathways for mental health research and interventions.