Artificial Intelligence-Based Models for Predicting Vaccines Critical Tweets: An Experimental Study

Uzair Shah*, Hazrat Ali, Tanvir Alam, Mowafa Househ, Zubair Shah

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We studied the suitability of Artificial Intelligence (AI)-based models to predict vaccine-critical tweets on the social media platform Twitter. We manually labeled a sample of 800 tweets as either 'vaccine-critical' (i.e, anti-vaccine tweets, mentioned concerns related to vaccine safety and efficacy, and are against vaccine mandates or vaccine passports) or 'other' (i.e., tweets that are neutral, report news, or are ambiguous) and used them to train and test AI-based models for automatically predicting vaccine-critical tweets. We fine-tuned two pre-trained deep learning-based language models, BERT and BERTweet, and implemented four classical AI-based models, Random Forest, Logistics Regression, Linear Support Vector Machines, and Multinomial Naïve Bayes. We evaluated these AI-based models using f1 score, accuracy, precision, and recall in three-fold cross-validation. We found that BERTweet outperformed all other models using these measures.

Original languageEnglish
Title of host publicationAdvances in Informatics, Management and Technology in Healthcare
EditorsJohn Mantas, Parisis Gallos, Emmanouil Zoulias, Arie Hasman, Mowafa S. Househ, Marianna Diomidous, Joseph Liaskos, Martha Charalampidou
PublisherIOS Press BV
Pages209-212
Number of pages4
ISBN (Electronic)9781643682907
DOIs
Publication statusPublished - 2022

Publication series

NameStudies in Health Technology and Informatics
Volume295
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Keywords

  • deep learning
  • machine learning
  • tweets
  • vaccines

Fingerprint

Dive into the research topics of 'Artificial Intelligence-Based Models for Predicting Vaccines Critical Tweets: An Experimental Study'. Together they form a unique fingerprint.

Cite this