Detecting Conspiracy Theory Against COVID-19 Vaccines

TL;DR

The paper investigates conspiracy theories about COVID-19 vaccines on social media by applying two NLP approaches—BERT-based sentiment analysis and Google Perspective API—to 598 English-language comments from North American sources. It evaluates multiple classifiers, finding that Perspective with Gaussian Naive Bayes yields the highest accuracy (~75%), while a BERT-based approach with Logistic Regression reaches about 69%, with performance improving as more data are added. The work demonstrates a practical framework for quantifying sentiment and toxicity in vaccine-related discourse, informing moderation and public health communications, though its geographic and dataset size limitations call for broader, multilingual studies. Overall, the study contributes a data-driven lens on how conspiracy content relates to vaccine hesitancy and how automated tools can help monitor and address it.

Abstract

Since the beginning of the vaccination trial, social media has been flooded with anti-vaccination comments and conspiracy beliefs. As the day passes, the number of COVID- 19 cases increases, and online platforms and a few news portals entertain sharing different conspiracy theories. The most popular conspiracy belief was the link between the 5G network spreading COVID-19 and the Chinese government spreading the virus as a bioweapon, which initially created racial hatred. Although some disbelief has less impact on society, others create massive destruction. For example, the 5G conspiracy led to the burn of the 5G Tower, and belief in the Chinese bioweapon story promoted an attack on the Asian-Americans. Another popular conspiracy belief was that Bill Gates spread this Coronavirus disease (COVID-19) by launching a mass vaccination program to track everyone. This Conspiracy belief creates distrust issues among laypeople and creates vaccine hesitancy. This study aims to discover the conspiracy theory against the vaccine on social platforms. We performed a sentiment analysis on the 598 unique sample comments related to COVID-19 vaccines. We used two different models, BERT and Perspective API, to find out the sentiment and toxicity of the sentence toward the COVID-19 vaccine.

Figures (5)

• Figure 1: Word Distribution of the Dataset.
• Figure 2: Label Distribution of the Dataset.
• Figure 3: Performance Comparison of Two Models.
• Figure 4: Perspective Accuracy, F1 Score, Recall, and the Precision.
• Figure 5: BERT Model Accuracy, F1 Score, Recall, and Precision.