The Ability of Pretrained Large Language Models in Understanding Health Concepts in Social Media Posts

Lay people’s terms of health concepts are widely found in social medial data. Understanding their terms can help learn what they have experienced. The existing consumer health vocabularies do not include many health concept phrases found in social media. Recent advancement of pretrained large language models has demonstrated their state-of-the-art performance in a number of natural language processing tasks. In this work, we investigated 3 commonly used pretrained large language models on their ability of understanding consumer health concepts. The results on a corpus of 156 phrases related to 3 common COVID-19 symptoms showed that these pretrained general domain language models generated encouraging outputs, indicating that they may be a promising alternative to the current consumer health vocabularies.