BACKGROUND
The COVID-19 pandemic has created a pressing need for integrating information from disparate sources, in order to assist decision makers. Social media is important in this respect, however, to make sense of the textual information it provides and be able to automate the processing of large amounts of data, natural language processing methods are needed. Social media posts are often noisy, yet they may provide valuable insights regarding the severity and prevalence of the disease in the population. In particular, machine learning techniques for triage and diagnosis could allow for a better understanding of what social media may offer in this respect.
OBJECTIVE
This study aims to develop an end-to-end natural language processing pipeline for triage and diagnosis of COVID-19 from patient-authored social media posts, in order to provide researchers and other interested parties with additional information on the symptoms, severity and prevalence of the disease.
METHODS
The text processing pipeline first extracts COVID-19 symptoms and related concepts such as severity, duration, negations, and body parts from patients’ posts using conditional random fields. An unsupervised rule-based algorithm is then applied to establish relations between concepts in the next step of the pipeline. The extracted concepts and relations are subsequently used to construct two different vector representations of each post. These vectors are applied separately to build support vector machine learning models to triage patients into three categories and diagnose them for COVID-19.
RESULTS
We report that Macro- and Micro-averaged F_{1\ }scores in the range of 71-96% and 61-87%, respectively, for the triage and diagnosis of COVID-19, when the models are trained on human labelled data. Our experimental results indicate that similar performance can be achieved when the models are trained using predicted labels from concept extraction and rule-based classifiers, thus yielding end-to-end machine learning. Also, we highlight important features uncovered by our diagnostic machine learning models and compare them with the most frequent symptoms revealed in another COVID-19 dataset. In particular, we found that the most important features are not always the most frequent ones.
CONCLUSIONS
Our preliminary results show that it is possible to automatically triage and diagnose patients for COVID-19 from natural language narratives using a machine learning pipeline, in order to provide additional information on the severity and prevalence of the disease through the eyes of social media.
RACAI's Natural Language Processing pipeline for Universal Dependencies
