One of the most talked-about topics in the world today is climate change, which has sparked a lot of public discussion on social media. Particularly on Twitter, users regularly express their opinions, worries, and attitudes regarding climate-related subjects, making it a valuable source of current public opinion. Automated sentiment analysis is a useful solution because manually analysing these massive amounts of textual data is difficult and time-consuming. This study uses Twitter data to analyse public opinion on climate change using a machine learning-based methodology. The suggested system gathers tweets about climate change and uses a variety of natural language processing methods, including stopword removal, tokenisation, text cleaning, and lemmatisation. In order to determine attitudes like positive, negative, or neutral, the processed data is subsequently transformed using a vectorisation technique and classed using a trained machine learning model. Additionally, users can enter text and receive real-time sentiment forecasts using a web-based interface created with Flask. The suggested approach shows how social media analytics and machine learning may be successfully integrated to comprehend how the public views climate change and promote data-driven environmental awareness and decision-making