Enhancing Health Mention Classification Performance: A Study on Advancements in Parameter Efficient Tuning

2025-04-30

AI Summary

Health Mention Classification (HMC) faces challenges in fine-grained recognition due to metaphorical and descriptive expressions, hindering real-time public health surveillance from social media. To address this, we propose a lightweight and efficient modeling framework that— for the first time—integrates part-of-speech (POS) tags with an enhanced parameter-efficient fine-tuning (PEFT) paradigm. Our approach injects syntactic structural priors into Transformer-based biomedical language models via unified integration of Adapter, LoRA, and hybrid PEFT strategies. Evaluated on three benchmark datasets—RHDM, PHM, and Illness—our method achieves new state-of-the-art F1-scores across all. The model size is reduced by over 40%, and training speed is accelerated by more than 3×. Our core contribution is a syntax-aware lightweight PEFT paradigm, which significantly improves small-model generalization and discriminative capability for implicit health-related expressions.

Technology Category

• Natural Language Processing: Syntax — Tagging, Chunking & Parsing
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Health Mention Classification (HMC) plays a critical role in leveraging social media posts for real-time tracking and public health monitoring. Nevertheless, the process of HMC presents significant challenges due to its intricate nature, primarily stemming from the contextual aspects of health mentions, such as figurative language and descriptive terminology, rather than explicitly reflecting a personal ailment. To address this problem, we argue that clearer mentions can be achieved through conventional fine-tuning with enhanced parameters of biomedical natural language methods (NLP). In this study, we explore different techniques such as the utilisation of part-of-speech (POS) tagger information, improving on PEFT techniques, and different combinations thereof. Extensive experiments are conducted on three widely used datasets: RHDM, PHM, and Illness. The results incorporated POS tagger information, and leveraging PEFT techniques significantly improves performance in terms of F1-score compared to state-of-the-art methods across all three datasets by utilising smaller models and efficient training. Furthermore, the findings highlight the effectiveness of incorporating POS tagger information and leveraging PEFT techniques for HMC. In conclusion, the proposed methodology presents a potentially effective approach to accurately classifying health mentions in social media posts while optimising the model size and training efficiency.

Problem

• Improving health mention classification in social media posts
• Addressing challenges from figurative language in health mentions
• Enhancing performance with parameter-efficient tuning and POS tags

Innovation

• Utilizing POS tagger information for HMC
• Improving PEFT techniques for efficiency
• Combining methods to enhance F1-score