A clustering approach to filtering unfair testimonies for reputation systems

The problem of unfair testimonies remains an open issue in reputation systems for online trading communities. A common attempt is to use binary ratings to model sellers’ reputation. However, this attempt leads to that the research of tackling unfair testimonies also focuses on reputation systems using binary ratings. In this extended abstract, we propose a two-stage clustering approach to filter unfair testimonies for reputation systems using multi-nominal ratings. The proposed approach uses clustering to identify unfair testimonies and further contributes to providing buyers a more accurate reputation evaluation regarding the target seller.