Enhanced Analysis of Global Warming Sentiments Using Twitter Data

Global warming is a widely recognized pressing global issue. Online platforms like Twitter (now X), have significantly influenced general opinion on this topic, often emphasizing the divide between those who accept and reject the reality of climate change. To better understand public perceptions and emotions surrounding this critical issue, this study uses Twitter (now X) data to analyze sentiment toward climate change. By employing cutting-edge ML and NLP strategies, the proposed method classified tweets as positive, negative, neutral, and news sentiment categories. The linear support vector classifier (LSVC) attained optimal outcomes in accuracy, precision, recall, and F1 measure (73.31%, 73.71%, 73.31%, and 71.73%), respectively. These findings provide key insights into public opinions toward global warming and highlight the effectiveness of the LSVC approach. Future research could focus on classifying classification models, incorporating multi modal data, and exploring deep learning approaches to extend climate change sentiment analysis across various platform for social media.