Dutch Metaphor Extraction from Cancer Patients' Interviews and Forum Data using LLMs and Human in the Loop

TL;DR

This study explores extracting Dutch cancer patient metaphors from interviews and online forums using large language models with human verification, aiming to improve healthcare communication and patient care.

Contribution

It introduces a novel approach combining LLMs and human-in-the-loop verification to extract metaphors from Dutch cancer patient data, creating a new corpus for healthcare communication research.

Findings

LLMs can effectively identify metaphors with proper prompting strategies.

Human verification improves the accuracy of metaphor extraction.

The resulting corpus supports better patient-clinician communication.

Abstract

Metaphors and metaphorical language (MLs) play an important role in healthcare communication between clinicians, patients, and patients' family members. In this work, we focus on Dutch language data from cancer patients. We extract metaphors used by patients using two data sources: (1) cancer patient storytelling interview data and (2) online forum data, including patients' posts, comments, and questions to professionals. We investigate how current state-of-the-art large language models (LLMs) perform on this task by exploring different prompting strategies such as chain of thought reasoning, few-shot learning, and self-prompting. With a human-in-the-loop setup, we verify the extracted metaphors and compile the outputs into a corpus named HealthQuote.NL. We believe the extracted metaphors can support better patient care, for example shared decision making, improved communication between patients and clinicians, and enhanced patient health literacy. They can also inform the design of personalized care pathways. We share prompts and related resources at https://github.com/4dpicture/HealthQuote.NL