# Figurative Usage Detection of Symptom Words to Improve Personal Health Mention Detection

## TL;DR

This paper enhances personal health mention detection by integrating figurative language detection, leading to improved accuracy in identifying health-related sentences that use symptom words figuratively.

## Contribution

It introduces two methods combining figurative usage detection with CNN-based health mention detection, demonstrating improved performance.

## Key findings

- 2.21% average F-score improvement with feature augmentation approach
- Effective integration of figurative language detection enhances health mention detection accuracy
- Shows potential for better health information extraction from social media

## Abstract

Personal health mention detection deals with predicting whether or not a given sentence is a report of a health condition. Past work mentions errors in this prediction when symptom words, i.e. names of symptoms of interest, are used in a figurative sense. Therefore, we combine a state-of-the-art figurative usage detection with CNN-based personal health mention detection. To do so, we present two methods: a pipeline-based approach and a feature augmentation-based approach. The introduction of figurative usage detection results in an average improvement of 2.21% F-score of personal health mention detection, in the case of the feature augmentation-based approach. This paper demonstrates the promise of using figurative usage detection to improve personal health mention detection.