Abstract
This article studies how a recommender system may incentivize users to learn about a product collaboratively. To improve the incentives for early exploration, the optimal design trades off fully transparent disclosure by selectively overrecommending the product (or “spamming”) to a fraction of users. Under the optimal scheme, the designer spams very little on a product immediately after its release but gradually increases its frequency; she stops it altogether when she becomes sufficiently pessimistic about the product. The recommender’s product research and intrinsic/naive users “seed” incentives for user exploration and determine the speed and trajectory of social learning. Potential applications for various Internet recommendation platforms and implications for review/ratings inflation are discussed.