Analyzing COVID-19 Vaccination Sentiments in Nigerian Cyberspace: Insights from a Manually Annotated Twitter Dataset
Ibrahim Said Ahmad, Lukman Jibril Aliyu, Abubakar Auwal Khalid, Saminu Muhammad Aliyu, Shamsuddeen Hassan Muhammad, Idris Abdulmumin, Bala Mairiga Abduljalil, Bello Shehu Bello, Amina Imam Abubakar
TL;DR
This study analyzes Nigerian public sentiment toward COVID-19 vaccination using a manually annotated Twitter dataset of 4,320 tweets collected from late 2020 to mid-2022. It combines exploratory data analysis with a comparative modeling framework that includes classical machine learning and fine-tuned large language models (e.g., XLM-RoBERTa, Afro-XLMR, BERT). Results show a predominately neutral stance, with a nontrivial positive minority, and demonstrate that fine-tuned LLMs outperform classical models on this small, multilingual dataset. The work provides a publicly available dataset and demonstrates the practicality of LLM fine-tuning for vaccine sentiment analysis in Nigeria, suggesting paths for real-time public opinion monitoring and policy support. The conclusions acknowledge dataset size and label imbalance as limitations and propose targeted hyperparameter and preprocessing improvements for future work.
Abstract
Numerous successes have been achieved in combating the COVID-19 pandemic, initially using various precautionary measures like lockdowns, social distancing, and the use of face masks. More recently, various vaccinations have been developed to aid in the prevention or reduction of the severity of the COVID-19 infection. Despite the effectiveness of the precautionary measures and the vaccines, there are several controversies that are massively shared on social media platforms like Twitter. In this paper, we explore the use of state-of-the-art transformer-based language models to study people's acceptance of vaccines in Nigeria. We developed a novel dataset by crawling multi-lingual tweets using relevant hashtags and keywords. Our analysis and visualizations revealed that most tweets expressed neutral sentiments about COVID-19 vaccines, with some individuals expressing positive views, and there was no strong preference for specific vaccine types, although Moderna received slightly more positive sentiment. We also found out that fine-tuning a pre-trained LLM with an appropriate dataset can yield competitive results, even if the LLM was not initially pre-trained on the specific language of that dataset.