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. C 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

@en

Today, around 260.000 people in the Netherlands are diagnosed with dementia. This paper provides a first design and evaluation of a social robot that provides the music which supports positive self-disclosures of personal memories. Based on the situated cognitive engineering methodology, we developed software for the Pepper robot which can let people with dementia (PwD) listen to their favorite music and we tested this robot in a care center with seven persons with dementia. The test focused on robot’s usability and music’s effect on the person listening. Three general claims were tested: The robot (1) is easy to use by the PwD, relatives and caregivers, (2) brings PwD in a more positive emotional state, and (3) stimulates PwD to recall memories and talk about their past.
Our results show that the "music robot" for PwD often elicits very strong positive responses and that our observations are in line with the three claims. However, using a very human-like robot like Pepper does pose certain challenges as the PwD expect it to truly understand every word they say, which is not yet the case.@en

Today, around 260.000 people in the Netherlands are diagnosed with dementia. This paper provides a first design and evaluation of a social robot that provides the music which supports positive self-disclosures of personal memories. Based on the situated cognitive engineering methodology, we developed software for the Pepper robot which can let people with dementia (PwD) listen to their favorite music and we tested this robot in a care center with seven persons with dementia. The test focused on robot’s usability and music’s effect on the person listening. Three general claims were tested: The robot (1) is easy to use by the PwD, relatives and caregivers, (2) brings PwD in a more positive emotional state, and (3) stimulates PwD to recall memories and talk about their past.
Our results show that the "music robot" for PwD often elicits very strong positive responses and that our observations are in line with the three claims. However, using a very human-like robot like Pepper does pose certain challenges as the PwD expect it to truly understand every word they say, which is not yet the case.@en