Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features

TLDR

Social media is increasingly used to share personal health information, yet its informal, nontechnical language makes extracting medical concepts difficult, and progress in applying advanced machine‑learning NLP has been limited. The study aims to develop a machine‑learning system to extract adverse drug reaction mentions from informal social‑media text for pharmacovigilance. ADRMine is a CRF‑based concept extraction system that incorporates a novel word‑cluster feature derived from unsupervised clustering of pretrained word embeddings generated from unlabeled social‑media posts. ADRMine achieves an F‑measure of 0.82, outperforming strong baselines, and feature analysis shows that the word‑cluster features markedly improve performance, enabling scalable extraction of complex medical concepts from informal user posts with minimal annotated data.

Abstract

Social media is becoming increasingly popular as a platform for sharing personal health-related information. This information can be utilized for public health monitoring tasks, particularly for pharmacovigilance, via the use of natural language processing (NLP) techniques. However, the language in social media is highly informal, and user-expressed medical concepts are often nontechnical, descriptive, and challenging to extract. There has been limited progress in addressing these challenges, and thus far, advanced machine learning-based NLP techniques have been underutilized. Our objective is to design a machine learning-based approach to extract mentions of adverse drug reactions (ADRs) from highly informal text in social media.We introduce ADRMine, a machine learning-based concept extraction system that uses conditional random fields (CRFs). ADRMine utilizes a variety of features, including a novel feature for modeling words' semantic similarities. The similarities are modeled by clustering words based on unsupervised, pretrained word representation vectors (embeddings) generated from unlabeled user posts in social media using a deep learning technique.ADRMine outperforms several strong baseline systems in the ADR extraction task by achieving an F-measure of 0.82. Feature analysis demonstrates that the proposed word cluster features significantly improve extraction performance.It is possible to extract complex medical concepts, with relatively high performance, from informal, user-generated content. Our approach is particularly scalable, suitable for social media mining, as it relies on large volumes of unlabeled data, thus diminishing the need for large, annotated training data sets.