Sentiment Analysis of Public Opinion on Climate Change Education using Social Media Data

Abstract

Climate change is a global challenge that significantly affects the environment, human health, and social well-being. Climate change education plays a vital role in fostering public awareness and encouraging participation in mitigation and adaptation efforts. This study aims to analyze public sentiment toward climate change issues using social media data as a representation of global opinion. The dataset used in this study is the public “Climate Change Tweets” dataset from Kaggle, which contains tweets posted between January 1 and July 19, 2022. The research employs a text-based sentiment analysis approach using Natural Language Processing (NLP) techniques in Python, involving several stages including data cleaning, preprocessing, sentiment classification, and visualization. Sentiment classification was conducted using TextBlob, categorizing tweets into positive, neutral, and negative sentiments. The results indicate that the majority of tweets express neutral sentiment (100%), with no significant presence of positive or negative tones. The generated word cloud highlights dominant terms such as climate council, insideclimatenews, and greta thunberg, reflecting that discussions around climate change on Twitter primarily focus on information sharing and environmental advocacy. These findings suggest that online discourse on climate change tends to be informative and fact-driven, emphasizing the dissemination of credible information rather than emotional reactions. This study underscores the crucial role of social media as an effective medium to support education and raise global awareness about climate change.