It’s Difficult to Be Neutral – Human and LLM-based Sentiment Annotation of Patient Comments

Petter Mæhlum, David Samuel, Rebecka Maria Norman, Elma Jelin, Øyvind Andresen Bjertnæs, Lilja Øvrelid, Erik Velldal


Abstract
Sentiment analysis is an important tool for aggregating patient voices, in order to provide targeted improvements in healthcare services. A prerequisite for this is the availability of in-domain data annotated for sentiment. This article documents an effort to add sentiment annotations to free-text comments in patient surveys collected by the Norwegian Institute of Public Health (NIPH). However, annotation can be a time-consuming and resource-intensive process, particularly when it requires domain expertise. We therefore also evaluate a possible alternative to human annotation, using large language models (LLMs) as annotators. We perform an extensive evaluation of the approach for two openly available pretrained LLMs for Norwegian, experimenting with different configurations of prompts and in-context learning, comparing their performance to human annotators. We find that even for zero-shot runs, models perform well above the baseline for binary sentiment, but still cannot compete with human annotators on the full dataset.
Anthology ID:
2024.cl4health-1.2
Volume:
Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Dina Demner-Fushman, Sophia Ananiadou, Paul Thompson, Brian Ondov
Venues:
CL4Health | WS
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
8–19
Language:
URL:
https://aclanthology.org/2024.cl4health-1.2
DOI:
Bibkey:
Cite (ACL):
Petter Mæhlum, David Samuel, Rebecka Maria Norman, Elma Jelin, Øyvind Andresen Bjertnæs, Lilja Øvrelid, and Erik Velldal. 2024. It’s Difficult to Be Neutral – Human and LLM-based Sentiment Annotation of Patient Comments. In Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024, pages 8–19, Torino, Italia. ELRA and ICCL.
Cite (Informal):
It’s Difficult to Be Neutral – Human and LLM-based Sentiment Annotation of Patient Comments (Mæhlum et al., CL4Health-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.cl4health-1.2.pdf