Martijn Willemsen The recommender LAB of Martijn Willemsen researches how decisions can be supported by recommender systems, and includes domains such as movies, music, health related decisions and energy-saving measures. The LAB focuses on how insights from decision psychology can improve recommender algorithms, how to best evaluate recommender systems and on novel recommendation methods that help users with developing preferences and goals.

Energy recommendations

Bart Knijnenburg developed our first recommender system in our lab, which was a content-based energy savings recommender. This recommender system was used to test different methods of preference elicitation that would fit with different levels of domain expertise of the user. Our overview paper (Knijnenburg et al. 2014) summarizes the research and shows that if the preference elicitation method matches the domain knowledge, users experience higher system satisfaction and choice satisfaction, and also select more energy measures that attain higher energy savings.

Relevant research papers:

  • Knijnenburg, B.P., Willemsen, M.C., & Broeders, R.(2014). Smart Sustainability through System Satisfaction: Tailored Preference Elicitation for Energy-saving Recommenders. Full paper accepted to the Americas Conference on Information Systems (AMCIS) manuscript
  • Knijnenburg, B. P., Reijmer, N. J. M., & Willemsen, M. C. (2011). Each to his own: how different users call for different interaction methods in recommender systems. In Proceedings of the fifth ACM conference on Recommender systems (pp. 141–148). New York, NY, USA: ACM. free access via ACM
  • Knijnenburg, B.P. & Willemsen, M.C. (2010). The effect of preference elicitation methods on the user experience of a recommender system. CHI EA '10 : Proceedings of the 28th of the international conference extended abstracts on Human factors in computing systems, (pp. 3457-3462). New York: ACM. free access via ACM
  • Knijnenburg, B.P., Willemsen, M.C. (2009). Understanding the effect of adaptive preference elicitation methods on user satisfaction of a recommender system. 3rd ACM Conference on Recommender Systems, RecSys'09, 23 October - 25 October 2009, New York, NY. (pp. 381-384). (Best short paper award RecSys 2009) free access via ACM

Rasch-based Energy recommendations

With PhD student Alain Starke, we extended the earlier energy-saving recommender work using Rasch-based recommendations. This type of recommendation assumes that energy saving measures can be ordered on a one-dimensional scale from easy to very difficult and that users can be mapped on this same scale by means of their energy saving ability (Starke et al., 2015). Different from existing recommendation approaches that mostly recommend items that fit what users like and do now, a rasch-based recommender can help users to move forward and improve their energy-saving abilities (Starke et al., 2017).

Starke2017 - Effective User Interface Designs to Increase Energy-efficient Behavior in a Rasch-based Energy Recommender System from Alain Starke

Relevant research papers:

  • Starke, A., Willemsen, M., & Snijders, C. (2017). Effective User Interface Designs to Increase Energy-efficient Behavior in a Rasch-based Energy Recommender System. In Proceedings of the Eleventh ACM Conference on Recommender Systems (pp. 65–73). New York, NY, USA: ACM. free access via ACM
  • Starke, A.D., Willemsen, M.C., & Snijders, C.(2015). Saving Energy in 1-D: Tailoring Energy-saving Advice Using a Rasch-based Energy Recommender System. CEUR-WS Workshop Proceedings, Vol. 1533, 5-8. (Proceedings of the 2nd International Workshop on Decision Making and Recommender Systems, Bolzano, Italy, October 22-23, 2015). link to paper