Detecting Emerging Symptoms of COVID-19 using Context-based Twitter Embeddings

TL;DR

This paper introduces an iterative graph-based method for detecting evolving COVID-19 symptoms from Twitter data, which can identify symptom mentions earlier than official reports and generalizes to adverse drug reaction detection.

Contribution

The paper presents a novel graph-based approach for context-specific symptom detection in social media, applicable to emerging diseases and adverse drug reactions.

Findings

Detects COVID-19 symptoms before CDC reports

Generalizes to adverse drug reaction detection

Effective in large imbalanced Twitter corpora

Abstract

In this paper, we present an iterative graph-based approach for the detection of symptoms of COVID-19, the pathology of which seems to be evolving. More generally, the method can be applied to finding context-specific words and texts (e.g. symptom mentions) in large imbalanced corpora (e.g. all tweets mentioning #COVID-19). Given the novelty of COVID-19, we also test if the proposed approach generalizes to the problem of detecting Adverse Drug Reaction (ADR). We find that the approach applied to Twitter data can detect symptom mentions substantially before being reported by the Centers for Disease Control (CDC).