Feature importance scores of the predictors.
<div><p>Non-Suicidal Self-Injury (NSSI) is a prevalent and complex behavior among adolescents, often linked to negative emotions such as loneliness, anxiety, and emptiness. Traditional self-report and experimental methods rely on autobiographical recall and are therefore vulnerable to bi...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | , , , , , |
| 出版: |
2025
|
| 主題: | |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | <div><p>Non-Suicidal Self-Injury (NSSI) is a prevalent and complex behavior among adolescents, often linked to negative emotions such as loneliness, anxiety, and emptiness. Traditional self-report and experimental methods rely on autobiographical recall and are therefore vulnerable to bias and low ecological validity. Accordingly, approaches that repeatedly sample NSSI-related feelings and contexts in daily life such as Ecological Momentary Assessment (EMA) are needed. This study aimed to identify emotional predictors of NSSI thoughts among adolescents using machine learning and multilevel logistic regression. The study included 42 adolescents (aged 12–15 years) who had engaged in NSSI in the past year. Participants reported their mood and NSSI behaviors three times daily over a 14-day EMA period via a smartphone application. Predictor variables included depression, anxiety, loneliness, self-anger, anger towards others, shame, and emptiness. A random forest model identified loneliness (feature importance: 0.40), anxiety (0.18), and emptiness (0.14) as the most significant predictors of NSSI thoughts. Multilevel logistic regression confirmed these findings, showing that each one-unit increase in anxiety, loneliness, and emptiness corresponded to a 24%, 19%, and 24% increase in the odds of experiencing NSSI thoughts, respectively. The ICC value of 0.26 indicated substantial between-individual variance, justifying multilevel modeling. However, random effects analysis revealed no significant individual differences, suggesting uniform effects across participants. These findings highlight loneliness as the most influential predictor, emphasizing the need to address social connections in interventions. Combining machine learning with traditional statistical methods enhanced interpretability, providing practical insights for developing tailored, emotion-focused interventions for adolescents engaging in NSSI.</p></div> |
|---|