Dutch Metaphor Extraction from Cancer Patients’ Interviews and Forum Data Using LLMs and Human in the Loop

Abstract

Metaphors and Metaphorical Languages (MLs) play an important role in healthcare for the information communication between clinicians, patients, and patients’ family members. In this work, we focus on the Dutch language and cancer patients’ data. We extract the metaphors used by patients using two data resources: 1) cancer patient storytelling interview data, 2) online forum, data including cancer patients’ posts, comments, and questions to professionals. We investigate how current state of the art LLMs and perform on this task by exploring different prompting strategies such as Chain of Thought, few-shot learning, and self-prompting. With human in the loop, we verify the extracted metaphors and collect the output as a corpus, named “HealthQuote.NL”. We believe the extracted metaphors can be useful for supporting better patient care, e.g. shared decision making, helping communication between patients and clinicians, patient health literacy, etc. It can also be integrated into the design of a care path. We share our prompts and resources at https://github.com/4dpicture/HealthQuote.NL

Resources

Details