SynSym: A Synthetic Data Generation Framework for Psychiatric Symptom Identification

2026-03-22

AI Summary

This work addresses the scarcity of large-scale, symptom-level annotated data in mental health research—a limitation stemming from the high cost of expert annotation and the absence of standardized diagnostic guidelines—which hinders models’ ability to generalize across diverse symptom expressions. To overcome this, we propose SynSym, a novel framework that systematically integrates fine-grained symptom subconcepts, multi-style linguistic expressions, and clinical co-occurrence patterns to generate high-fidelity, diverse synthetic symptom data using large language models. Experiments demonstrate that models trained solely on SynSym-generated data achieve performance comparable to those trained on real-world data across three depression symptom benchmarks. Furthermore, fine-tuning with only a small amount of real data yields additional gains, confirming SynSym’s effectiveness in enhancing model generalization while substantially reducing reliance on costly human annotations.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Humanities & Computational Social Science

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Psychiatric symptom identification on social media aims to infer fine-grained mental health symptoms from user-generated posts, allowing a detailed understanding of users' mental states. However, the construction of large-scale symptom-level datasets remains challenging due to the resource-intensive nature of expert labeling and the lack of standardized annotation guidelines, which in turn limits the generalizability of models to identify diverse symptom expressions from user-generated text. To address these issues, we propose SynSym, a synthetic data generation framework for constructing generalizable datasets for symptom identification. Leveraging large language models (LLMs), SynSym constructs high-quality training samples by (1) expanding each symptom into sub-concepts to enhance the diversity of generated expressions, (2) producing synthetic expressions that reflect psychiatric symptoms in diverse linguistic styles, and (3) composing realistic multi-symptom expressions, informed by clinical co-occurrence patterns. We validate SynSym on three benchmark datasets covering different styles of depressive symptom expression. Experimental results demonstrate that models trained solely on the synthetic data generated by SynSym perform comparably to those trained on real data, and benefit further from additional fine-tuning with real data. These findings underscore the potential of synthetic data as an alternative resource to real-world annotations in psychiatric symptom modeling, and SynSym serves as a practical framework for generating clinically relevant and realistic symptom expressions.

Problem

• psychiatric symptom identification
• synthetic data generation
• mental health
• social media
• dataset construction

Innovation

• synthetic data generation
• psychiatric symptom identification
• large language models
• clinical co-occurrence
• mental health NLP