From Tweets to Energy Trends (TwEn): An exploratory framework for machine learning-based forecasting of urban-scale energy behavior leveraging social media data

摘要: Understanding energy dynamics is crucial in addressing climate change, yet the accuracy of energy predictions is often limited by reliance on oversimplified static data, failing to represent dynamic, non-linear occupancy-related dimensions. This study aims to develop an exploratory framework, From Tweets to Energy Trends (TwEn), leveraging machine learning and geo-tagged social media big data to explore the social dynamics of urban energy behavior. The framework explores the correlation between social media interactions, especially the frequency of tweets using data from the X Platform, and energy use patterns on an hourly basis. Employing various machine learning models, including Artificial Neural Networks (ANN), decision trees (DTREE), random forests (RDF), and gradient boosting machines (GBM), the study evaluates their efficiency in both static and dynamic (time-series) forecasting energy use …