Skip to main content
QUICK REVIEW

[论文解读] Who We Are, Where We Are: Mental Health at the Intersection of Person, Situation, and Large Language Models

Nikita Soni, August Nilsson|arXiv (Cornell University)|Mar 6, 2026
Mental Health via Writing被引用 0
一句话总结

该论文提出理论基础、可解释的模型,将个体特征与情境8 DIAMONDS特征与HaRT基嵌入相结合,以在纵向社交媒体数据中预测幸福感并检测自我状态的适应性/非适应性。它将原则性基线与心理测量学信息驱动的语言模型进行比较,并分析可解释性的预测特征。

ABSTRACT

Mental health is not a fixed trait but a dynamic process shaped by the interplay between individual dispositions and situational contexts. Building on interactionist and constructionist psychological theories, we develop interpretable models to predict well-being and identify adaptive and maladaptive self-states in longitudinal social media data. Our approach integrates person-level psychological traits (e.g., resilience, cognitive distortions, implicit motives) with language-inferred situational features derived from the Situational 8 DIAMONDS framework. We compare these theory-grounded features to embeddings from a psychometrically-informed language model that captures temporal and individual-specific patterns. Results show that our principled, theory-driven features provide competitive performance while offering greater interpretability. Qualitative analyses further highlight the psychological coherence of features most predictive of well-being. These findings underscore the value of integrating computational modeling with psychological theory to assess dynamic mental states in contextually sensitive and human-understandable ways.

研究动机与目标

  • 将心理学理论与NLP连接,建模在情境中的动态心理健康状态。
  • 将个体层面特征与情境8 DIAMONDS特征整合为一个 principled 基线。
  • 利用HaRT为个体-情境嵌入来捕捉语言的时间动态。
  • 评估幸福感以及自我状态的适应性/非适应性预测性能。
  • 提供定性洞见,指出哪些心理特征与幸福感关系最强。

提出的方法

  • 构建一个 principled 基线,将S8D情境特征与四个PLT子领域(隐性动机、心理健康、韧性、认知扭曲)相结合。
  • 使用Deepseek-R1少-shot提示对帖子进行八维S8D注释。
  • 在句级和帖子级计算19个PLT特征,使用RoBERTa-Large、情感/和谐/满意度/焦虑/抑郁指数,以及ReLM韧性 facets。
  • 对HaRT进行微调,以从时间历史中生成面向人-情境的嵌入,用于帖子级和句级预测。
  • 在帖子级评估连续幸福感(岭回归),在句级评估适应性/非适应性标签(逻辑回归)。
  • 使用嵌套的5折交叉验证评估模型,并设定阈值以提取证据级注释。
Figure 1: Distribution of probabilities to predict adaptive state for a given sentence. On the top is using HaRTWB-FT + PLT features, and the bottom is using PLT features in Logistic Regression models.
Figure 1: Distribution of probabilities to predict adaptive state for a given sentence. On the top is using HaRTWB-FT + PLT features, and the bottom is using PLT features in Logistic Regression models.

实验结果

研究问题

  • RQ1一个理论基础的基线,结合S8D与PLT特征,能否与心理测量语言模型一样有效或更好地预测幸福感?
  • RQ2HaRT的人-情境嵌入是否在幸福感和自我状态证据检测方面提供额外的预测能力,超出 principled 基线?
  • RQ3在纵向社交媒体数据中,哪些心理特征与幸福感和适应性/非适应性自我状态的相关性最强?

主要发现

  • 帖子中的情境特征(S8D)可预测标注的幸福感分数。
  • 将S8D与PLT特征相结合的 principled 基线,在性能上优于单一特征组。
  • 基于HaRT的人-情境嵌入在内部验证中优于基线预测幸福感,且组合特征集实现最强性能。
  • 基于HaRT的模型在识别适应性和非适应性证据范围方面效果显著,较基线特征对语言变异的敏感性更高。
  • 定性分析强调幸福感与生活满意度、生活和谐及积极性之间的正相关,以及与某些韧性与认知扭曲指标的负相关。
Figure 2: Qualitative analysis of features in our principled baseline consisting of psychological characteristics of the situation and person-level traits. Left: Pearson correlation coefficients; Right: Ridge regression beta coefficients for predicting well-being with the S8D and PLT features.
Figure 2: Qualitative analysis of features in our principled baseline consisting of psychological characteristics of the situation and person-level traits. Left: Pearson correlation coefficients; Right: Ridge regression beta coefficients for predicting well-being with the S8D and PLT features.

更好的研究,从现在开始

从论文设计到论文写作,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。