Q-rater: A collaborative reputation system based on source credibility theory

The consumer is an important information source and the after-transaction-feedback is used as the quality indicator for trust building in e-commerce. However, the possibility of incorrect information from unreliable users and declining trust in the electronic market looms large. Hence, there is a need for a fairer and more objective reputation mechanism. Most existing reputation systems focus on the reputation of users than items and they rely on explicit feedback information. As a solution to these problems, we propose a reputation system (“Q-rater”) suitable for B2C e-commerce. We adopt the source credibility theory of consumer psychology and the basic mechanism of collaborative filtering methods for the overall process of the proposed reputation system. We also evaluate performance of the Q-rater experimentally by comparing it with the other benchmark systems and observing the performance changes with variations in the size of rater group and item rating aggregation mechanism.