Trust and reputation systems represent a significant trend in decision support for Internet mediated service provision. The basic idea is to let parties rate each other, for example after the completion of a transaction, and use the aggregated ratings about a given party to derive a trust or reputation score, which can assist other parties in deciding whether or not to transact with that party in the future. A natural side effect is that it also provides an incentive for good behaviour, and therefore tends to have a positive effect on market quality. Reputation systems can be called collaborative sanctioning systems to reflect their collaborative nature, and are related to collaborative filtering systems. Reputation systems are already being used in successful commercial online applications. There is also a rapidly growing literature around trust and reputation systems, but unfortunately this activity is not very coherent. The purpose of this article is to give an overview of existing and proposed systems that can be used to derive measures of trust and reputation for Internet transactions, to analyse the current trends and developments in this area, and to propose a research agenda for trust and reputation systems.

Reputation systems can be used in online markets and communities in order to stimulate quality and good behaviour as well as to sanction poor quality and bad behaviour. The basic idea is to have a mechanism for rating services on various aspects, and a way of computing reputation scores based on the ratings from many different parties. By making the reputation scores public, such systems can assist parties in deciding whether or not to use a particular service. Reputation systems represent soft security mechanisms for social control. This article presents a type of reputation system based on the Dirichlet probability distribution which is a multinomial Bayesian probability distribution. Dirichlet reputation systems represent a generalisation of the binomial Beta reputation system. The multinomial aspect of Dirichlet reputation systems means that any set of discrete rating levels can be defined. This provides great flexibility and usability, as well as a sound basis for designing reputation systems.

Reputation systems can be tricked by the spread of false reputation ratings, be it false accusations or false praise. Simple solutions such as exclusively relying on one's own direct observations have drawbacks, as they do not make use of all the information available. We propose a fully distributed reputation system that can cope with false disseminated information. In our approach, everyone maintains a reputation rating and a trust rating about everyone else that they care about. From time to time first-hand reputation information is exchanged with others; using a modified Bayesian approach we designed and present in this paper, only second-hand reputation information that is not incompatible with the current reputation rating is accepted. Thus, reputation ratings are slightly modified by accepted information. Trust ratings are updated based on the compatibility of second-hand reputation information with prior reputation ratings. Data is entirely distributed: someone's reputation and trust is the collection of ratings maintained by others. We enable redemption and prevent the sudden exploitation of good reputation built over time by introducing re-evaluation and reputation fading.

Semantic Web endeavors have mainly focused on issues pertaining to knowledge representation and ontology design. However, besides understanding information metadata stated by subjects, knowing about their credibility becomes equally crucial. Hence, trust and trust metrics, conceived as computational means to evaluate trust relationships between individuals, come into play. Our major contributions to Semantic Web trust management through this paper are twofold. First, we introduce our classification scheme for trust metrics along various axes and discuss advantages and drawbacks of existing approaches for Semantic Web scenarios. Hereby, we will devise our advocacy for local group trust metrics, guiding us to the second part which presents Appleseed, our novel proposal for local group trust computation. Compelling in its simplicity, Appleseed borrows many ideas from spreading activation models in psychology and relates their concepts to trust evaluation in an intuitive fashion.

The quality of a reputation system depends on the integrity of the ratings it receives as input. A fundamental problem is that a rater can rate an agent more positively or more negatively than the real experience with the agent would dictate. When ratings are provided by agents outside the control of the relying party, it is a priori impossible to know when a rater provides such unfair ratings. However, it is often the case that unfair ratings have a different statistical pattern than fair ratings. This paper uses that idea, and describes a statistical filtering technique for excluding unfair ratings, and illustrates its effectiveness through simulations.

Abstract. In many dynamic open systems, agents have to interact with one another to achieve their goals. Here, agents may be self-interested and when trusted to perform an action for another, may betray that trust by not performing the action as required. In addition, due to the size of such systems, agents will often interact with other agents with which they have little or no past experience. There is therefore a need to develop a model of trust and reputation that will ensure good interactions among software agents in large scale open systems. Against this background, we have developed TRAVOS (Trust and Reputation model for Agent-based Virtual OrganisationS) which models an agent’s trust in an interaction partner. Specifically, trust is calculated using probability theory taking account of past interactions between agents, and when there is a lack of personal experience between agents, the model draws upon reputation information gathered from third parties. In this latter case, we pay particular attention to handling the possibility that reputation information may be inaccurate. 1

Trust is an essential component of successful interactions in social life as well as in business relationships. In this paper we propose a system that closely reflects real-world trust building in an online environment. We describe the models used to represent trust in entities in various categories, algorithms to calculate and update trust based on experiences of entities with each other and the agent interactions necessary for finding and exchanging trust information.

Abstract. Interactions between entities unknown to each other are inevitable in the ambient intelligence vision of service access anytime, anywhere. Trust management through a reputation mechanism to facilitate such interactions is recognized as a vital part of mobile ad hoc networks, which features lack of infrastructure, autonomy, mobility and resource scarcity of composing light-weight terminals. However, the design of a reputation mechanism is faced by challenges of how to enforce reputation information sharing and honest recommendation elicitation. In this paper, we present a reputation model, which incorporates two essential dimensions, time and context, along with mechanisms supporting reputation formation, evolution and propagation. By introducing the notion of recommendation reputation, our reputation mechanism shows effectiveness in distinguishing truth-telling and lying agents, obtaining true reputation of an agent, and ensuring reliability against attacks of defame and collusion. 1

This research aims to develop a model of trust and reputation that will ensure good interactions amongst software agents in large scale open systems. The following are key drivers for our model: (1) agents may be self-interested and may provide false accounts of experiences with other agents if it is beneficial for them to do so; (2) agents will need to interact with other agents with which they have little or no past experience. Against this background, we have developed TRAVOS (Trust and Reputation model for Agentbased Virtual OrganisationS) which models an agent’s trust in an interaction partner. Specifically, trust is calculated using probability theory taking account of past interactions between agents. When there is a lack of personal experience between agents, the model draws upon reputation information gathered from third parties. In this latter case, we pay particular attention to handling the possibility that reputation information may be inaccurate.

Trust is an important tool in human life, as it enables people to cope with the uncertainty caused by the free will of others. Uncertainty and uncontrollability are also issues in computer-assisted collaboration and electronic commerce in particular. A computational model of trust and its implementation can alleviate this problem. This survey