华东师范大学学报(自然科学版) ›› 2025, Vol. 2025 ›› Issue (1): 124-137.doi: 10.3969/j.issn.1000-5641.2025.01.010

• 计算机科学 • 上一篇    

基于标签感知增强的社交媒体心理亚健康归因方法

梁怡萍, 肖路巍, 王琳琳*()   

  1. 华东师范大学 计算机科学与技术学院, 上海 200062
  • 收稿日期:2024-01-09 出版日期:2025-01-25 发布日期:2025-01-20
  • 通讯作者: 王琳琳 E-mail:llwang@cs.ecnu.edu.cn

Label-perception augmented causal analysis of mental health over social media

Yiping LIANG, Luwei XIAO, Linlin WANG*()   

  1. School of Computer Science and Technology, East China Normal University, Shanghai 200062, China
  • Received:2024-01-09 Online:2025-01-25 Published:2025-01-20
  • Contact: Linlin WANG E-mail:llwang@cs.ecnu.edu.cn

摘要:

在大量的网络社交媒体中, 存在一些表达了潜在的心理健康障碍和精神疾病的帖子, 根据帖子文本识别用户产生心理健康障碍的原因是一项重要任务. 观察这些帖子发现, 其上下文中存在标签共现现象, 即上下文中同时出现了多个候选标签的语义, 干扰了标签表征的建模与预测. 为缓解该现象带来的影响, 提出了一种标签感知增强分类的方法, 该方法利用大规模预训练语言模型识别潜在的候选标签, 并通过估计样本独立的标签语义强度作为增强数据以消减共现标签带来的噪声, 基于增强数据构建了性能良好的预训练语言模型分类器. 在数据集Intent_SDCNL和SAD上进行的实验验证了该方法的有效性.

关键词: 心理亚健康归因, 自然语言处理, 提示学习

Abstract:

Online social media are frequently used by people as a way of expressing their thoughts and feelings. Among the vast amounts of online posts, there may be more concerning ones expressing potential grievances and mental illnesses. Identifying these along with potential causes of mental health problems is an important task. Observing these posts, it is found that there is a label co-occurrence phenomenon in contexts, i.e., the semantics of multiple candidate labels appear in the context of one sample, which interferes with the modeling and prediction of label patterns. To mitigate the impact of this phenomenon, we propose a label-aware data augmentation method, which leverages large-scale pre-trained language models with excellent text comprehension capability to identify potential candidate labels, abates the noise from irrelevant co-occurring labels by estimating sample-independent label semantic strengths, and constructs well-performing classifiers with pre-trained language models. Extensive experiments validate the effectiveness of our model on the recent datasets Intent_SDCNL and SAD.

Key words: causal analysis of mental health, natural language processing, prompt learning

中图分类号: