T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systems
arXiv:2107.08959
Abstract
Simulation has emerged as a popular method to study the long-term societal consequences of recommender systems. This approach allows researchers to specify their theoretical model explicitly and observe the evolution of system-level outcomes over time. However, performing simulation-based studies often requires researchers to build their own simulation environments from the ground up, which creates a high barrier to entry, introduces room for implementation error, and makes it difficult to disentangle whether observed outcomes are due to the model or the implementation. We introduce T-RECS, an open-sourced Python package designed for researchers to simulate recommendation systems and other types of sociotechnical systems in which an algorithm mediates the interactions between multiple stakeholders, such as users and content creators. To demonstrate the flexibility of T-RECS, we perform a replication of two prior simulation-based research on sociotechnical systems. We additionally show how T-RECS can be used to generate novel insights with minimal overhead. Our tool promotes reproducibility in this area of research, provides a unified language for simulating sociotechnical systems, and removes the friction of implementing simulations from scratch.
17 pages, 5 figures; updated Figure 2(b) after fixing small bug in replication code (see Github for more details)
References in corpus (8)
- Wide & Deep Learning for Recommender Systems
- Multisided Fairness for Recommendation
- Joint Deep Modeling of Users and Items Using Reviews for Recommendation
- RecSim: A Configurable Simulation Platform for Recommender Systems
- Balancing Information Exposure in Social Networks
- Do Offline Metrics Predict Online Performance in Recommender Systems?
- RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems
- An Agent-Based Model of Message Propagation in the Facebook Electronic Social Network