MISE: Meta-knowledge Inheritance for Social Media-Based Stressor Estimation

2025-04-22

The Web Conference

AI Summary

This work addresses the challenge of fine-grained stressor identification (e.g., “exams”, “thesis writing”) in social media text—characterized by a large number of categories, extremely limited per-class samples, and continual emergence of novel stressors—by formally introducing the few-shot stressor identification task. Methodologically, we propose a meta-learning framework based on a modified MAML algorithm, incorporating a semantic-enhanced text encoder and a transferable meta-knowledge memory module, along with a novel meta-knowledge inheritance mechanism to mitigate catastrophic forgetting during adaptation to unseen stressors. Evaluated on a newly constructed, publicly released dataset (hosted on Kaggle and Hugging Face), our model achieves state-of-the-art performance, demonstrating significant improvements in cross-stressor generalization and continual adaptability. This work establishes a new paradigm for mental health–oriented AI and provides a foundational benchmark resource.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Search and Optimization: Metareasoning and Metaheuristics
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web

Abstract

Stress haunts people in modern society, which may cause severe health issues if left unattended. With social media becoming an integral part of daily life, leveraging social media to detect stress has gained increasing attention. While the majority of the work focuses on classifying stress states and stress categories, this study introduce a new task aimed at estimating more specific stressors (like exam, writing paper, etc.) through users' posts on social media. Unfortunately, the diversity of stressors with many different classes but a few examples per class, combined with the consistent arising of new stressors over time, hinders the machine understanding of stressors. To this end, we cast the stressor estimation problem within a practical scenario few-shot learning setting, and propose a novel meta-learning based stressor estimation framework that is enhanced by a meta-knowledge inheritance mechanism. This model can not only learn generic stressor context through meta-learning, but also has a good generalization ability to estimate new stressors with little labeled data. A fundamental breakthrough in our approach lies in the inclusion of the meta-knowledge inheritance mechanism, which equips our model with the ability to prevent catastrophic forgetting when adapting to new stressors. The experimental results show that our model achieves state-of-the-art performance compared with the baselines. Additionally, we construct a social media-based stressor estimation dataset that can help train artificial intelligence models to facilitate human well-being. The dataset is now public at href{https://www.kaggle.com/datasets/xinwangcs/stressor-cause-of-mental-health-problem-dataset}{underline{Kaggle}} and href{https://huggingface.co/datasets/XinWangcs/Stressor}{underline{Hugging Face}}.

Problem

• Estimating specific stressors from social media posts
• Addressing few-shot learning for diverse, evolving stressors
• Preventing catastrophic forgetting in meta-learning for stressor estimation

Innovation

• Meta-learning for stressor estimation
• Meta-knowledge inheritance mechanism
• Few-shot learning for new stressors