The relationship between linguistic expression and symptoms of depression, anxiety, and suicidal thoughts: A longitudinal study of blog content

To investigate the associations between linguistic features and symptoms of depression, generalised anxiety, and suicidal ideation, we extracted linguistic features from individuals’ blog content and correlated it with validated mental health data in a longitudinal study (n=38). Depressive symptoms were assessed using the self-report Patient Health Questionnaire (PHQ-9), anxiety symptoms using the self-report Generalised Anxiety Disorder Scale (GAD-7), and social media data was analysed using the Linguistic Inquiry and Word Count (LIWC) tool for linguistic features. Bivariate and multivariate analyses were performed to investigate the correlations between the linguistic features and mental health scores between subjects. We then used the multivariate regression model to predict longitudinal changes in mood within subjects.为探究语言特征与抑郁、广泛性焦虑及自杀意念症状之间的关联，本项纵向研究（n=38）从受试者的博客内容中提取语言特征，并将其与经过验证的心理健康数据进行关联分析。抑郁症状采用患者健康问卷9项版（Patient Health Questionnaire, PHQ-9）自评量表进行评估，焦虑症状采用广泛性焦虑障碍量表7项版（Generalised Anxiety Disorder Scale, GAD-7）自评量表进行评估；研究使用语言查询与词数统计（Linguistic Inquiry and Word Count, LIWC）工具对社交媒体数据进行语言特征分析。随后开展双变量与多变量分析，以探究受试者间语言特征与心理健康评分的相关性；并进一步采用多变量回归模型，对受试者内部的情绪纵向变化进行预测。