Rewarding honest ratings through personalised recommendations in electronic commerce
Generate an AI Snapshot to get a quick, structured summary of this paper.
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper proposes an incentive mechanism, HYRIWYG (How You Rate Influences What You Get) that encourages the evaluators to volunteer their true opinions, by compensating users with rewards that reflect the quality of the RS to which they contribute.
Abstract
Recommender systems (RS) are important facilitators of electronic commerce as they enable the retrieval of useful information. However, it is crucial to motivate people to contribute truthful evaluations. This paper proposes an incentive mechanism, HYRIWYG (How You Rate Influences What You Get) that encourages the evaluators to volunteer their true opinions, by compensating users with rewards that reflect the quality of the RS to which they contribute. This effect is achieved through a redemption rule that limits the use of the incentives to products that the RS suggests based on the user's personal profile. The HYRIWYG is a general incentive mechanism that can be embedded in most existing recommender systems, as long as they calculate personalised profiles based on user feedback. The deployment of the HYRIWYG mechanism to support a collaborative filtering mechanism in the domain of movie ratings illustrates its usefulness in settings where user tastes are heterogeneous.
