Systematic Delineation of Media Polarity on COVID-19 Vaccines in Africa: Computational Linguistic Modeling Study (Preprint)

Abstract

BACKGROUND The global onset of the Coronavirus disease 2019 (COVID-19) has resulted in significant public health and socio-economic impacts. The necessity for an immediate medical breakthrough is unprecedentedly compelling. However, parallel to the emergence of the COVID-19 pandemic is the proliferation of information regarding the pandemic, which, if uncontrolled, can not only mislead the public, but also hinder the concerted efforts of relevant stakeholders in mitigating against the effect of this pandemic. It is known that media communications can significantly affect public perception and attitude towards a medical treatment, vaccinatiion or a subject matter, particularly when the population has limited knowledge on the subject. OBJECTIVE The presented study attempts to systematically scrutinize media communications (google news headlines/snippets and twitter posts) in order to understand prevailing sentiments regarding COVID-19 vaccines in Africa. METHODS This was achieved using three standard computational linguistics models - i.e., TextBlob, VADER, and Word2Vec-BiLSTM. RESULTS A total of 637 twitter posts and 569 google news headlines/descriptions retrieved between February 02, 2020 to May 05, 2020 were analyzed. Interestingly, the results revealed that contrary to general perceptions, google news headlines/snippets and twitter posts within the stated period were generally passive to positive towards COVID-19 vaccines in Africa. It was possible to understand these patterns in light of increasingly sustained efforts by various media and health actors in ensuring availability of healthy and factual information about the pandemic. CONCLUSIONS This type of analysis could contribute to understanding predominant polarities and associated potential attitudinal inclinations. Such knowledge could be critical in informing relevant public health and media engagement policies.