Automatic Processing of User-Generated Content for the Description of Energy-Consuming Activities at Individual and Group Level

Abstract

Understanding and improving the energy consumption behavior of individuals is considered a powerful approach to improve energy conservation and stimulate energy efficiency. To motivate people to change their energy consumption behavior, we need to have a thorough understanding of which energy-consuming activities they perform and how these are performed. Traditional sources of information about energy consumption, such as smart sensor devices and surveys, can be costly to set up, may lack contextual information, have infrequent updates, or are not publicly accessible. In this paper, we propose to use social media as a complementary source of information for understanding energy-consuming activities. A huge amount of social media posts are generated by hundreds of millions of people every day, they are publicly available, and provide real-time data often tagged to space and time. We design an ontology to get a better understanding of the energy-consuming activities domain and develop a text and image processing pipeline to extract from social media the description of energy-consuming activities. We run a case study on Istanbul and Amsterdam. We highlight the strength and weakness of our approach, showing that social media data has the potential to be a complementary source of information for describing energy-consuming activities.

Keywords

• social media
• energy-consuming activities
• energy consumption
• machine learning
• ontology