Todays modern smartphones are not only widely used, but also often equipped with GPS receivers and other sensors to allow constant monitoring of their users’ locations and in some cases even recognition of their activities. For this reason, these mobile devices are of particular interest for transport and mobility, where detailed movement data are needed not only for urban planning and smart city-related activities, but can also be of use for providing individual users with feedback and suggestions for personal behavior change.

In GoEco!, a large-scale study based in Switzerland (cf. [1, 2]), we have used such activity tracking data to provide people with eco-feedback on their personal mobility patterns and stimulation to adopt more energy-efficient mobility choices. Raising awareness of their mobility patterns and the entailing consequences in the users can be achieved by providing the optimal eco-feedback, defined as “feedback on individual or group behaviors with a goal of reducing environmental impact” [3], and is a necessary—though not sufficient—condition towards more sustainable mobility patterns (cf. [4]).

Generating suitable eco-feedback is a complex procedure involving different steps. Figure 1 illustrates the proposed system developed as part of the GoEco! Project. In order to induce behavioral change in the context of mobility choices, the three primary outputs of the system are:

  • Global analyses that compare an individual user with other people and provide an overview of how much someone travels and how this relates to greenhouse gas emissions;
  • Potential improvements with respect to all the journeys ever tracked by the system;
  • An analysis of frequently traveled loops and how each of them could individually be improved in terms of ecological sustainability.

These outputs are provided to the user as direct eco-feedback, both within the app and in analog form, but serve also to adjust the scopes of additional gamification elements, such as certain required behavior changes for achieving a goal or getting rewarded with a badge.

Figure 1: Data from the Moves® tracker app is fed into our transport mode classifier. The resulting mobility data are used to globally assess the behavior of an individual user, but also to analyze which routes are frequently traveled, and to identify potential improvements with respect to sustainability.

A first requirement for computing these outputs is to detect frequently traveled journeys of a user. This is achieved by spatially clustering visited points of interest, and splitting the journeys into individual loops, for example one which starts and ends at a user’s home. A frequency-based assessment allows us to determine which routes should be considered as systematic for this user. Secondly, we need to identify alternative travel options both for individually traveled routes, as well as complete loops. Several heuristics are used to generate a graph of potential modal choices (respecting travel durations, distances, and personal preferences), which is then analyzed regarding energy requirements and greenhouse gas emissions. The best (but still feasible) alternative journey (potentially consisting of multiple modes of transport) is then chosen for the overall user assessment, for generation of the gamified app elements and directly as a suggestion to the user to improve his or her mobility style. Figure 2 shows an exemplary travel alternative for a person traveling by tram.

 

Figure 2: An exemplary travel alternative, where a journey by foot and tram is replaced by a bicycle one.

We performed several surveys to assess the quality of the eco-feedback provided to the users. The results show that the process of identification of systematic trips was perceived as mostly correct by the test persons; the GoEco! users agreed that around 86% of all identified systematic loops were indeed traveled several times during the study period, and they themselves classified 69% of them as systematic. The identified alternatives were seen as feasible options in more than 50% of all cases. This result can be explained by the fact that for mode and mobility choices personal circumstances play an important role, but are rather difficult to automatically assess without any user interaction. Finally, we analyzed the potential effect of a hypothetical scenario in which all users are actually choosing the most sustainable alternative at all times, and found that especially systematically traveled journeys by car provide great potential for ecological improvement, as they are often relatively shorter and could potentially be replaced by public transport or bicycles.

The people involved in this project are Dominik Bucher, Francesca Cellina, Dr. Francesca Mangili, Claudio Bonesana, Dr. David Jonietz , Prof. Martin Raubal and Dr. Roman Rudel.

Prof. Raubal is an ESC member and Professor of Geoinformation Engineering at the Institute of Cartography and Geoinformation.

The Chair of Geoinformation Engineering has its research foci in the areas of mobility and energy. In the area of mobility, the group research lies at the intersection of mobile geographic information systems, geospatial information technologies, and mobile decision-making. In the area of energy, the focus is on the development of spatio-temporal algorithms to determine the technical and economic potential of renewable energy sources, and optimal locations for energy facilities and power lines.

References

[1] Dominik Bucher, Francesca Mangili, Claudio Bonesana, David Jonietz, Francesca Cellina, and Martin Raubal. Demo Abstract: Extracting eco-feedback information from automatic activity tracking to promote energy-efficient individual mobility behavior. Computer Science-Research and Development 33.1-2 (2018): 267-268.

[2]Francesca Cellina, Dominik Bucher, Martin Raubal, Roman Rudel, Vanessa de Luca, and Massimo Botta. GoEco!A set of smartphone apps supporting the transition towards sustainable mobility patterns. Change-IT Workshop at ICT for Sustainability (ICT4S), 2016.

[3] Jon Froehlich, Leah Findlater, and James Landay. The design of eco-feedback technology. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pages 1999-2008. ACM, 2010.

[4]Jon Froehlich. Gamifying green: gamication and environmental sustainability. In Steffen P Walz and Sebastian Deterding, editors, The Gameful World: Approaches, Issues, Applications, pages 563-596. Mit Press, London, 2015.