A SUPER‐AGENT‐BASED FRAMEWORK FOR REPUTATION MANAGEMENT AND COMMUNITY FORMATION IN DECENTRALIZED SYSTEMS. (21st January 2014)

• Record Type: Journal Article
• Authors: Wang, Yao; Zhang, Jie; Vassileva, Julita
• Is Part Of: Computational intelligence. Volume 30:Number 4(2014:Nov.)
• Page Start: 722
• Page End: 751
• Publication Date: 2014-01-21
• Subjects: Artificial intelligence -- Periodicals; Computational linguistics -- Periodicals; 006.3
• DOI: 10.1111/coin.12026
• Languages: English
• ISSNs: 0824-7935

Abstract

<abstract abstract-type="main" id="coin12026-abs-0001"> <title>Abstract</title> <p id="coin12026-para-0001">In this article, we propose a novel super‐agent‐based framework for reputation management and community formation in decentralized systems. We describe this framework in the context of Web service selection where agents with more capabilities act as super‐agents. These super‐agents serve as reputation managers to maintain reputation information of services and share the information with other consumer agents that have fewer capabilities than the super‐agents. In addition, super‐agents can maintain communities and build community‐based reputation for a service based on the opinions from all community members that have similar interests and judgement criteria as the super‐agents or the other community members. A practical reward mechanism is also introduced to create incentives for super‐agents to contribute their resources (to maintain reputation and form communities) and provide truthful reputation information. Experimental results obtained through simulation confirm that our approach achieves better effectiveness and scalability compared to the systems that do not use super‐agents and that do not form communities.</p> </abstract>