Biasness of World Leaders: A Sentiment Analysis of World Leaders’ Twitter Data

Abstract

The United Nations’ Sustainable Development Goals (SDGs) are a set of 17 goals that were adopted in 2015 as a blueprint for a better and more sustainable future. The goals are interconnected and address diverse global challenges such as poverty, inequality, climate change, peace, and justice. World leaders play an integral role in creating awareness and establishing policies that support attaining the goals. Understanding the opinions of world leaders towards the SDGs can help the United Nations (UN) identify areas of support and potential barriers to achieving the goals. Furthermore, it can be used by policymakers to design strategies to accelerate progress toward the SDGs. Twitter is a widespread social media platform founded in 2006 that allows users to send short messages called "tweets" containing up to 280 characters. It has over 350 million monthly active users as of 2023. Sentiment analysis on Twitter data can help researchers understand public opinions, attitudes, and emotions toward a particular viewpoint or an event. Researchers have been using Twitter data for multiple research purposes such as sentiment analysis due to its popularity and public availability. For instance, stock prices predictions, and public sentiments toward Covid19 outbreak This study aims to classify world leaders’ sentiments on the 17 Sustainable Development Goals (SDGs) using machine learning algorithms. English language Twitter data of world leaders has been collected from January 2015 to February 2023 and then labeled with SDGs ontologies. As per our research, there are no SDGs labeled world leaders’ Twitter data datasets publically available. We used a Python-based tool, SNScrape library to fetch world leaders’ Twitter data. There are other procedures to label a dataset but we prefer the ontology-based for this study since it is time efficient. This study performs an empirical comparison of different machine learning algorithms and evaluates effectiveness in classifying tweets based on their relevance to the 17 SDGs. The results provide a comprehensive picture of world leaders’ views and opinions on the SDGs, as expressed on social media, which can be used to inform decision-making and drive progress toward achieving the SDGs.