Using Explanations as Energy-Saving Frames: A User-Centric Recommender Study

Recommender systems usually seek to cater to the preferences of a single user. However, societal issues that involve multiple stakeholders, such as climate change, cannot be mitigated this way. We address this issue by going beyond traditional algorithms, using psychological theories to not only optimize what is recommended (i.e., the algorithm), but also how interface items are presented. We present the ‘Saving Aid’ recommender system for household energy conservation, encouraging users to adopt energy-saving measures with high kWh savings, such as buying environmentally-friendly electronic appliances. In an online user study (N = 258), we compare different interfaces that promote measures with high kWh savings using different framing techniques, presenting either a kWh savings score or a Smart Savings Score that combines effort and kWh savings. We show that framing positively affects the extent to which users consider kWh savings when choosing a measure, without compromising the user’s system evaluation.

[1]  Alain Starke,et al.  The Effectiveness of Advice Solicitation and Social Peers in an Energy Recommender System , 2019, IntRS@RecSys.

[2]  Martijn C. Willemsen,et al.  Behaviorism is Not Enough: Better Recommendations through Listening to Users , 2016, RecSys.

[3]  R. Newell,et al.  Nudging Energy Efficiency Behavior: The Role of Information Labels , 2013, Journal of the Association of Environmental and Resource Economists.

[4]  W. Poortinga,et al.  Values, Environmental Concern, and Environmental Behavior , 2004 .

[5]  L. Steg,et al.  Going green? The relative importance of feelings over calculation in driving environmental intent in the Netherlands and the United States , 2016 .

[6]  M. F. Luce,et al.  Constructive Consumer Choice Processes , 1998 .

[7]  Abbes Amira,et al.  A survey of recommender systems for energy efficiency in buildings: Principles, challenges and prospects , 2021, Inf. Fusion.

[8]  M. Eirinaki,et al.  Reducing energy waste in households through real-time recommendations , 2020, RecSys.

[9]  P. Stern,et al.  Personal and contextual influences on househould energy adaptations. , 1985 .

[10]  Florian G. Kaiser,et al.  The economy of E-waste collection at the individual level: A practice oriented approach of categorizing determinants of E-waste collection into behavioral costs and motivation , 2018, Journal of Cleaner Production.

[11]  Guy Champniss,et al.  Flip sides of the same coin? A simple efficiency score versus energy bill savings information to drive consumers to choose more energy-efficient products , 2018 .

[12]  Gerhard Friedrich,et al.  Recommender Systems - An Introduction , 2010 .

[13]  Martijn C. Willemsen,et al.  Effective User Interface Designs to Increase Energy-efficient Behavior in a Rasch-based Energy Recommender System , 2017, RecSys.

[14]  M. Dekay,et al.  Public perceptions of energy consumption and savings , 2010, Proceedings of the National Academy of Sciences.

[15]  Martijn C. Willemsen,et al.  With a little help from my peers: depicting social norms in a recommender interface to promote energy conservation , 2020, IUI.

[16]  W. Poortinga,et al.  Household preferences for energy-saving measures: A conjoint analysis , 2003 .

[17]  Steven Isley,et al.  Sustainability at scale: towards bridging the intention-behavior gap with sustainable recommendations , 2018, RecSys.

[18]  Mario Pandelaere,et al.  When and why attribute sorting affects attribute weights in decision-making , 2014 .

[19]  Wändi Bruine de Bruin,et al.  Changing Household Behaviors to Curb Climate Change: How Hard Can it Be? , 2011 .

[20]  Daniel G. Goldstein,et al.  Beyond nudges: Tools of a choice architecture , 2012 .

[21]  A. Tversky,et al.  The framing of decisions and the psychology of choice. , 1981, Science.

[22]  Gerhard Friedrich,et al.  Persuasive Recommendation: Serial Position Effects in Knowledge-Based Recommender Systems , 2007, PERSUASIVE.

[23]  M. Delmas,et al.  The Dynamics of Behavior Change: Evidence from Energy Conservation , 2016 .

[24]  Magali A. Delmas,et al.  Nonprice incentives and energy conservation , 2015, Proceedings of the National Academy of Sciences.

[25]  Martijn C. Willemsen,et al.  Beyond “one-size-fits-all” platforms: Applying Campbell's paradigm to test personalized energy advice in the Netherlands , 2020 .

[26]  M. R. Espejo.  Applying the Rasch Model: Fundamental Measurement in the Human Sciences , 2004 .

[27]  Bart P. Knijnenburg,et al.  Evaluating Recommender Systems with User Experiments , 2015, Recommender Systems Handbook.

[28]  Yong Zheng,et al.  Utility-Based Multi-Stakeholder Recommendations by Multi-Objective Optimization , 2018, 2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI).

[29]  Bart P. Knijnenburg,et al.  Understanding the effect of adaptive preference elicitation methods on user satisfaction of a recommender system , 2009, RecSys '09.

[30]  Alain Starke,et al.  RecSys Challenges in achieving sustainable eating habits , 2019, HealthRecSys@RecSys.

[31]  F. Kaiser,et al.  Reviving Campbell’s Paradigm for Attitude Research , 2010, Personality and social psychology review : an official journal of the Society for Personality and Social Psychology, Inc.

[32]  T. Bond.  Applying the Rasch Model: Fundamental Measurement in the Human Sciences, Second Edition , 2001 .

[33]  L. Steg,et al.  Normative, Gain and Hedonic Goal Frames Guiding Environmental Behavior , 2007 .

[34]  Martijn C. Willemsen,et al.  Saving Energy in 1-D: Tailoring Energy-saving Advice Using a Rasch-based Energy Recommender System , 2015, DMRS.

[35]  Dimitrios Tzovaras,et al.  Redefining Micro-Moments for Improving Energy Behaviour: The SIT4Energy Approach , 2019, 2019 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI).

[36]  A. D. Starke,et al.  Supporting energy-efficient choices using Rasch-based recommender interfaces , 2019 .

[37]  Gerald Häubl,et al.  Preference Construction and Persistence in Digital Marketplaces: The Role of Electronic Recommendation Agents , 2001 .

[38]  Iraklis Varlamis,et al.  REHAB-C: Recommendations for Energy HABits Change , 2020, Future Gener. Comput. Syst..

[39]  Martijn C. Willemsen,et al.  Rasch-based tailored goals for nutrition assistance systems , 2019, IUI.

[40]  Jeffrey Bennett,et al.  Attribute Framing in Choice Experiments: How Do Attribute Level Descriptions Affect Value Estimates? , 2011, Environmental and Resource Economics.