Ramón Hermoso

Organising MAS: a formal model based on organisational mechanisms

In this paper, we propose a general formal framework for organising multiagent systems whose participants are rational agents. This model is based on the idea of organisational mechanisms. These are mechanisms introduced in a multiagent system with the aim of influencing the behaviour of the agents towards more effectiveness with regard to some objectives. We define two kinds of organisational mechanisms: i) informative mechanisms which provide additional information to agents, that may persuade agents to behave in a certain way, and ii) regulative mechanisms which produce changes in the environment of the agents, that may impose certain behaviours. We also define some properties of these mechanisms which will make it possible to prove certain characteristics of organised multiagent systems. Finally, we present a discussion about how the social concepts proposed by different organisational paradigms can be considered as either informative or regulative organisational mechanisms.

Integrating Trust in Virtual Organisations

Organisational models cannot only be used to structure multiagent systems but also to express behaviour constraints for agents in open environments. However, sometimes these behaviour constraints cannot be exhaustively enforced, and some agents may transgress the norms put forward by a Virtual Organisation. This poses an additional burden on agents, as they cannot be sure that their acquaintances will behave as prescribed. Trust and reputation mechanisms are of particular relevance to this respect, as they are commonly used to infer expectations of future behaviour from past interactions. In this paper we argue that, on the one hand, the a priori structure of Virtual Organisations can be useful to improve the efficiency of trust and reputation mechanisms, and that, on the other hand, such mechanisms provide relevant information for agents that are part of Virtual Organisations. For this purpose, we identify relevant aspects of existing organisational (meta-)models, and outline a reputation mechanism for Virtual Organisations that integrates these aspects. The dynamics of this mechanism is illustrated by an example.

Decision making matters: A better way to evaluate trust models

Trust models are mechanisms that predict behavior of potential interaction partners. They have been proposed in several domains and many advances in trust formation have been made recently. The question of comparing trust models, however, is still without a clear answer. Traditionally, authors set up ad hoc experiments and present evaluation results that are difficult to compare - sometimes even interpret - in the context of other trust models. As a solution, the community came up with common evaluation platforms, called trust testbeds. In this paper we expose shortcomings of evaluation models that existing testbeds use; they evaluate trust models by combining them with some ad hoc decision making mechanism and then evaluate the quality of trust-based decisions. They assume that if all trust models use the same decision making mechanism, the mechanism itself becomes irrelevant for the evaluation. We hypothesized that the choice of decision making mechanism is in fact relevant. To test our claim we built a testbed, called Alpha testbed, that can evaluate trust models either with or without decision making mechanism. With it we evaluated five well-known trust models using two different decision making mechanisms. The results confirm our hypothesis; the choice of decision making mechanisms influences the performance of trust models. Based on our findings, we recommend to evaluate trust models independently of the decision making mechanism - and we also provide a method (and a tool) to do so.

A Hybrid Reputation Model Based on the Use of Organizations

In this paper we present a hybrid reputation model focused on organizational structures that attempts to solve problems associated with both centralized and decentralized reputation models. Agents in our approach are able not only to evaluate the behavior of others and store reputations values but also to send such information to a centralized mechanism and ask for reputations to this one and to other agents. The main objective of our approach is to allow agents to reason about the reputation values that they receive. Therefore, together with the reputation values, agents store and send information about norms violated and fulfilled and about the facts that contributed to such behavior. Furthermore, this model provides two different types of reputations, as service provider that is related to the behavior of an agent while providing a service to other agents and as reputation source that is related to the behavior of an agent while providing reputation of others.

From blurry numbers to clear preferences: A mechanism to extract reputation in social networks

Complex social networks are typically used in order to represent and structure social relationships that do not follow a predictable pattern of behaviour. Due to their openness and dynamics, these networks make participants continuously deal with uncertainty before any type of interaction. Reputation appears as a key concept helping users to mitigate such uncertainty. Most of the reputation mechanisms proposed in the literature are based on numerical opinions (ratings), and consequently, they are exposed to potential problems such as the subjectivity in the opinions and their consequent inaccurate aggregation. With these problems in mind, this paper presents a reputation mechanism based on the concepts of pairwise elicitation processes and knock-out tournaments. The main objective of this mechanism is to build reputation rankings from qualitative opinions, thereby removing the subjectivity problems associated with the aggregation of quantitative opinions. The proposed approach is evaluated with different data sets from the MovieLens and Flixster web sites.

On the inaccuracy of numerical ratings: dealing with biased opinions in social networks

In this work, we study the potential problems emanating from using numerical ratings in social networks to rank entities regarding their reputation. In particular, we empirically demonstrate how reputation rankings as collected and managed by current systems are likely to be skewed due to subjectivity problems associated with the use of numerical ratings to encapsulate preferences. With the aim of overcoming these problems, we put forward an approach in which users are asked for their opinions about entities in a comparative fashion. In order to select the most appropriate users to be queried, we take advantage of the social structure derived from the interactions among users and entities following a principle of heterogeneity. Finally, we evaluate the proposed approach in the domain of movie ratings by using real datasets collected from different web sites.

An Adaptive Sanctioning Mechanism for Open Multi-agent Systems Regulated by Norms

This work presents an adaptive sanctioning mechanism that can be applied in open multi-agent systems that are regulated through norms. This mechanism tries to identify the attributes of the environment that have some influence on agents decision making and uses such attributes to define sanctions that may prevent norm violations. Our approach adapts sanctions to particular agents and particular environmental states. The mechanism is deployed by using an infrastructure of institutional agents in charge of adapting and applying sanctions to external agents. The proposal is evaluated empirically in a p2p scenario, comparing it with a traditional sanctioning approach for normative systems.

Effective use of organisational abstractions for confidence models

Trust and reputation mechanisms are commonly used to infer expectations of future behaviour from past interactions. They are of particular relevance when agents have to choose appropriate counterparts for their interactions as it may also happen within virtual organisations. However, when agents join an organisation, information about past interactions is usually not available. The use of organisational structures can tackle this problem and can improve the efficiency of trust and reputation mechanisms by endowing agents with some extra information to choose the best agents to interact with. In this context, we present how certain structural properties of virtual organisations can be used to build an efficient trust model in a local way. Furthermore, we introduce a testbed (TOAST) that allows to analyse different trust and reputation models in situations where agents act within virtual organisations. We experimentally evaluate our approach and show its validity.

DataGenCARS: A generator of synthetic data for the evaluation of context-aware recommendation systems

Abstract Context-Aware Recommender Systems (CARS) have started to attract significant research attention in the last years, due to the interest of considering the context of the user in order to offer him/her more appropriate recommendations. However, the evaluation of CARS is a challenge, due to the scarce availability of appropriate datasets that incorporate context information related to the ratings provided by the users. In this paper, we present DataGenCARS, a complete Java-based synthetic dataset generator that can be used to obtain the required datasets for any type of scenario desired, allowing a high flexibility in the obtention of appropriate data that can be used to evaluate CARS. The generator presents features such as: a flexible definition of user schemas, user profiles, types of items, and types of contexts; a realistic generation of ratings and attributes of items; the possibility to mix real and synthetic datasets; functionalities to analyze existing datasets as a basis for synthetic data generation; and support for the automatic mapping between item schemas and Java classes. Moreover, an experimental evaluation illustrates the interest and the benefits provided by DataGenCARS.

Artifacting and Regulating the Environment of a Virtual Organization

This work presents an extension of the Environment Dimension of the Virtual Organization Model, which is an Organization Modeling Language to define Organization-Centered Multi-Agent Systems. This extension allows this model to regulate the environment by supporting artifacts for organizational mechanisms, an approach based on the Agents & Artifacts conceptual framework. The three main entities of this framework are agents, artifacts and workspaces, which have been integrated in this work inside the Virtual Organization Model. Additionally, this paper presents an application to the health care setting and an analysis of the related work on this topic.