A Hybrid ML Sentiment Analysis for Climate Change Management in Social Media

Abstract

Carbon dioxide and other greenhouse gas emissions into the biosphere cause global warming, which in turn causes climate change. Sentiment analysis, particularly on microblogging platforms like Twitter, has garnered a lot of attention from academics in recent years due to the mountain of data generated by contemporary climate change arguments. However, there is a dearth of research on the effectiveness of different sentiment analysis methods via lexicon, machine learning, and mixed methods, particularly when it comes to this specific sentiment peculiar to this area. This research aims to assess and distinguish between several sentiment analysis methods to identify the best method for assessing tweets on climate change and related subjects. Seven lexicon-based techniques—SentiWordNet, VADER, SentiStrength, TextBlob, Hu and Liu, and WKWSCI—were used in this study.