自然语言处理心理测量学

中文摘要 AI 辅助

预测心理健康结果的自然语言处理（NLP）模型很少明确说明它们测量的是：上下文知识、情感内容还是句法结构。自然语言处理心理测量学将从文本进行心理预测视为一个心理测量问题，将分数与可解释的语言证据关联起来，并在训练文本格式之外进行测试。九种大型语言模型（LLM）在受控角色（认知数字影子）的条件下，完成了包含每个项目文本解释的心理测量问卷。我们通过文本思维网络（textual forma mentis networks）提取情感特征和句法-语义结构，结合人格和社会人口统计学变量，在 ablation 随机森林（RF）回归器中，使用 SHAP 识别哪些特征驱动了性能以及驱动方向。完整的 RF 模型解释了生活满意度（SWLS）高达 70.8% 的方差、抑郁（PHQ-9）55.7% 的方差；对于 DASS-21，其抑郁、焦虑、压力的方差解释率分别为 68.5%、76.0%、72.4%。仅社会人口统计学变量无法解释抑郁、焦虑或压力的有意义方差，但能解释生活满意度的方差，其中情感特征和收入是最强预测因子；而神经质和网络拓扑则主导抑郁和焦虑，且二者的影响方向相反。在不重新训练的情况下，RF 模型将日记与低分、高分角色区分开（相关系数 r 高达 0.91），且仅使用网络/情感特征时，在真实转录本中对临床参与者与对照参与者进行分类，准确率高达 68%。这些结果显示了合成数据的前景与局限：LLM 角色可揭示模型偏差、恢复与临床反刍一致的模式，并支持无需匹配问卷的人类文本心理测量预测，但无法替代人类验证。自然语言处理心理测量学通过可解释 AI 和网络/情感特征，使这些区分变得明确、可测量且可测试。

英文摘要

Natural Language Processing (NLP) models predicting mental health outcomes rarely specify what they measure: contextual knowledge, emotional content, or syntactic structure. NLP Psychometrics treats psychological prediction from text as a psychometric problem, linking scores to interpretable linguistic evidence and testing beyond the training text format. Nine LLMs, conditioned on controlled personas (cognitive digital shadows), completed psychometric questionnaires with textual explanations per item. We extracted emotional profiles and syntactic-semantic structure via textual forma mentis networks, combined with personality and sociodemographic variables in ablated random forest (RF) regressors, using SHAP to identify which features drove performance and in which direction. Full RF models explained up to 70.8% of variance in life satisfaction (SWLS), 55.7% in depression (PHQ-9), and, for DASS-21, 68.5% depression, 76.0% anxiety, 72.4% stress. Sociodemographics alone explained no meaningful variance in depression, anxiety, or stress, but did so for life satisfaction, where emotion features and income were the strongest predictors; neuroticism and network topology instead dominated depression and anxiety, reversing direction between them. Without retraining, RF models separated diaries from low- and high-score personas ($r$ up to 0.91) and, using only network/emotion features, classified clinical from control participants in real transcripts with up to 68% accuracy. These results show the promise and limits of synthetic data: LLM personas can expose model biases, recover patterns consistent with clinical rumination, and support psychometric prediction from human text without a matched questionnaire, but cannot substitute for human validation. NLP Psychometrics makes these distinctions explicit, measurable, and testable through interpretable AI and network/emotional features.

发表机构

• University of Trento（特伦托大学）

机构由 AI 辅助整理，请以论文原文为准。