Book Chapter Published

Abstract

During the COVID-19 pandemic, we witnessed the fastest massive vaccine rollout in human history. Like any other drug, vaccines have side effects, which might be harmful to the public trust when not properly communicated, hampering vaccination campaigns planned by governments. Therefore, it is of strategic importance to provide AI-empowered tools for monitoring their communication and feedback of social media users.

At the same time, adverse drug event extraction from user-generated content has gained popularity as a tool to aid researchers and pharmaceutical companies in monitoring the side effects of drugs in a real-world setting.

Using these innovative pharmacovigilance (PV) tools, it is possible to use natural language processing (NLP) techniques to monitor social media outlets and gain insights on how the population is reacting to information about the pandemic, vaccines, and measurement to contain infections, both from a psychological and physiological perspective.

Data collected from social media allow us to draw comparisons between the different areas of the world, times, and living conditions, discovering meaningful patterns. Indeed, some of the socio-economic factors that characterize different geographical areas (e.g., general lifestyle, food choices, sports activities, ethnicity, economic status etc.) can have a tangible impact on the population's understanding and adherence to therapies, containing measures and more in general and diseases.

In this article, we explore the possibilities of NLP for PV in the form of gathering and analyzing social media signals. We use as a case study the recent COVID-19 pandemic and show how the data collected on social media platforms such as Twitter since the start of the vaccination campaigns can provide useful insights and how this could help in future critical situations.

Keywords

Adverse drug events, Artificial Intelligence, COVID-19, Natural language processing, Pharmacovigilance