Recommender systems for nudging commuters towards eco-friendly decisions

Abstract

The rising urbanisation as well as the fact that work and leisure life become progressively geographically distributed lead to increased CO_2 emissions from citizens' activities related to traffic and mobility. One promising method to reduce CO_2 emissions from these activities is to encourage green transportation habits through recommendation and personalization technologies. Such technologies can support users in finding trips that cause low emissions and in the long term change their behaviour and habits. In this work we focus on travel recommenders and aim to provide urban travellers with a system that will nudge them to plan routes while considering the environmentally friendliest travel modes. We present a novel, ecologically-aware approach for travel recommender systems and describe our system implementation that incorporates dimensions of choice architecture. Our aim is to nudge users towards following routes that are environmentally friendly with lower CO_2 emissions than of those they usually take. Our implementation leverages the routing options and results of a commercial routing engine rendering it potentially applicable to any city. Furthermore it is integrated in a route planning assistant for android mobile phones and everyday use through a client - server architecture. An initial qualitative evaluation with a selected group of users shows that the recommender provides useful results including routes with reduced CO_2 emissions that users would not have considered without the recommender.