The utilization of social media in epidemic surveillance has been well established. Nonetheless, bias is often introduced when pre-defined lexicons are used to retrieve relevant corpus. This study introduces a framework aimed at curating extensive dictionaries of medical colloquialisms and Unified Medical Language System (UMLS) concepts. The framework comprises three modules: a BERT-based Named Entity Recognition (NER) model that identifies medical entities from social media content, a deep-learning powered normalization module that standardizes the extracted entities, and a semi-supervised clustering module that assigns the most probable UMLS concept to each standardized entity. We applied this framework to COVID-19-related tweets from February 1, 2020, to April 30, 2022, generating a symptom dictionary (available at https://github.com/ningkko/UMLS_colloquialism/) composed of 9,249 standardized entities mapped to 876 UMLS concepts and 38,175 colloquial expressions. This framework demonstrates encouraging potential in addressing the constraints of keyword matching information retrieval in social media-based public health research.

翻译：社交媒体在流行病监测中的应用已得到充分证实。然而，当使用预定义词汇表检索相关语料库时，往往会引入偏差。本研究提出了一种框架，旨在构建包含医学口语术语和统一医学语言系统（UMLS）概念的广泛词典。该框架包含三个模块：基于BERT的命名实体识别（NER）模块，用于从社交媒体内容中识别医学实体；深度学习驱动的标准化模块，用于规范提取的实体；以及半监督聚类模块，用于为每个标准化实体分配最可能的UMLS概念。我们将此框架应用于2020年2月1日至2022年4月30日期间与COVID-19相关的推文中，生成了一个症状词典（可在https://github.com/ningkko/UMLS_colloquialism/获取），该词典包含映射到876个UMLS概念的9,249个标准化实体和38,175个口语表达。该框架在解决基于社交媒体的公共卫生研究中关键词匹配信息检索的局限性方面展现了良好的潜力。