Recommender systems research is concerned with many aspects of recommender system behavior and effects than simply its effectiveness, and simulation can be a powerful tool for uncovering these effects. In this brief position paper, I identify specific types of research that simulation is uniquely well-suited to address along with a hierarchy of simulation types.
@article{arxiv.2110.00811,
title = {Multiversal Simulacra: Understanding Hypotheticals and Possible Worlds Through Simulation},
author = {Michael D. Ekstrand},
journal= {arXiv preprint arXiv:2110.00811},
year = {2021}
}
Comments
Contribution to the SimuRec Workshop at RecSys 2021