On Analyzing Estimation Errors due to Constrained Connections in Online Review Systems
This addresses the issue of biased reviews in online platforms, but it appears incremental as it focuses on analyzing an existing phenomenon without introducing new solutions.
The paper tackled the problem of how constrained connections in online review systems lead to poor estimation performance, finding that it negatively impacts both estimation accuracy and the Bayesian Cramer Rao lower bound.
Constrained connection is the phenomenon that a reviewer can only review a subset of products/services due to narrow range of interests or limited attention capacity. In this work, we study how constrained connections can affect estimation performance in online review systems (ORS). We find that reviewers' constrained connections will cause poor estimation performance, both from the measurements of estimation accuracy and Bayesian Cramer Rao lower bound.