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).
@article{arxiv.2011.03983,
title = {Detecting Emerging Symptoms of COVID-19 using Context-based Twitter Embeddings},
author = {Roshan Santosh and H. Andrew Schwartz and Johannes C. Eichstaedt and Lyle H. Ungar and Sharath C. Guntuku},
journal= {arXiv preprint arXiv:2011.03983},
year = {2020}
}
Comments
In proceedings of EMNLP 2020 (Empirical Methods in NLP) workshop on COVID-19