Les communautés virtuelles ont de plus en plus d’influence dans nos activités quotidiennes. Qu’elles soient sociales, d’affaires, professionnelles, d’apprentissage, ces communautés sont en concurrence pour la conquête de l'Internet, en ciblant une audience de plus en plus large et en proposant une offre de services de plus en plus variée. Par voie de conséquence, le succès ou l'échec de ces communautés dépend largement des services proposés dont la diversité, la qualité et l'adaptation sont les facteurs clés de satisfaction des clients. C’est pourquoi la démarche SOA (Service Oriented Architecture /Architecture Orientée Service) favorise la vision d'environnements ouverts où services, fournisseurs et clients sont indépendants les uns des autres, grâce au découplage et à l'allocation dynamique des services. Malheureusement, les environnements de communautés virtuelles ne prennent pas vraiment en compte les principes SOA et sont considérés fermés d’un point de vue des services offerts car ceux-ci sont limités aux fonctionnalités de la plateforme qui les hébergent. Cette dépendance des services vis-à-vis de la plateforme est considérée comme une limitation qui influence d'une manière négative le succès et la durabilité des communautés virtuelles. Du point de vue des membres d’une communauté, cette limitation entraine le départ de certains d’entre eux, et/ou impose à ses membres de joindre d'autres communautés afin de bénéficier des services offerts par ces dernières qui ne sont pas disponibles dans leur communauté d'origine. Du point de vue de l’environnement, l'introduction de nouveaux services nécessite de modifier la plateforme existante, et peut demander dans certains cas une migration vers une autre plateforme, ce qui peut perturber la communauté en question lorsque celle-ci est opérationnelle avec des membres en ligne. Dans ce contexte, ce travail a pour but de palier les limites de la gestion de services dans les communautés virtuelles afin de satisfaire les besoins de leurs membres, d'assurer une meilleure gestion des services d'un point de vue individuel et d'un point de vue de la communauté, et de garantir une évolution dynamique des services au sein de la communauté. L’objectif principal est donc de " Fournir le bon service, au bon utilisateur, au bon moment et avec la bonne qualité". L’hypothèse fondatrice de ce travail est que les communautés virtuelles peuvent être construites en commençant par un ensemble minimal de services de base, cet ensemble pouvant ensuite être étendu par l'ajout de nouveaux services selon les besoins des membres de la communauté. En adoptant cette approche, nous proposons un cadre de gestion de services qui aborde les difficultés rencontrées par les communautés virtuelles et leurs membres. En conséquence, le focus porte sur la satisfaction de ces membres plutôt que sur le service lui-même ou le fournisseur du service. Ainsi, nous définissons une nouvelle structuration des services au sein d’une communauté qui s’appuie sur une classification en différentes catégories fonctionnelles. Puis, nous étendons l'architecture SOA avec les concepts nécessaires pour modéliser ces catégories et leur associer un ensemble de propriétés non fonctionnelles de Qualité de Service (QdS ou QoS en anglais) utilisées par un système de médiation pour proposer les services adaptés aux besoins des usagers. Une description des unités fonctionnelles de ce système, ainsi que la façon dont elles opèrent, coopèrent et collaborent afin d'accomplir l’objectif défini ci-dessus constitue le cœur de notre contribution. / Virtual Communities are dominating our daily activities from different insights. Social, Business, Professional, Educational and many virtual communities are competing among each other to conquer the internet by targeting more audience through the services they provide. Consequently, the success or failure of virtual communities depends to a great extent on its services. In a world driven by services, diversity, quality and adaptation are key factors to achieve customer satisfaction. Accordingly the Service Oriented Architecture (SOA) approach promotes the vision of open environments where services, providers and consumers are considered independently from one another thanks to decoupling and dynamic allocation of services. But virtual communities environment did not really care about SOA and are considered closed with respect to the services they provide since they are bounded to the capabilities of the platform that host them. This implies the delivery of services inside the virtual communities is dependent on the platform used which is considered a limitation that have negative influence on the success and sustainability of virtual communities. From a member perspective this limitation causes community members to leave the community, and/or imposes them to join other virtual communities to benefit from the services they host and that are not available in their home virtual communities. From an environment perspective, introducing new services into these communities require modifications on the existing platforms or might require a complete shift to another platform in some cases which might affect the target community in case it is operational with active users. In this context, our research work aims to overcome the limitation in managing services of virtual community to satisfy community members’ needs, to provide better service management from a member perspective as well as from a community perspective, and to guarantee dynamic evolution of services inside the community. Our main objective is “To provide the right service to the right user in the right time with the required quality of service”. Our assumption is that virtual communities can be built starting from a minimal set of basic services and then add more services based on the needs of the community members. This drives us to adopt this approach and propose a service management framework that address the challenges faced by virtual communities and their members. Accordingly, we approach the problem from a members’ perspective and choose to work on members’ satisfaction more than we care about the service itself or the provider of the service. Thus, we define a new structure of services within a community that is based on a classification into different functional categories. Then, we extend SOA with the concepts necessary to model these categories and associate a set of non-functional properties of Quality of Service (QoS ) used by a mediation system to offer services best suited to the needs of members. Finally, we provide a description of the functional units of the system and how they operate, cooperate and collaborate to achieve the aforementioned objective. This is the core of our contribution.

The proliferation of services on the web is leading to the formation of service ecosystems wherein services interact with one another in ways not foreseen during their development or deployment. This means that over its lifetime, a service is likely to be reused across multiple interactions, such that in each of them a different interface is required from it. Implementing, testing, deploying, and maintaining adapters to deal with this multiplicity of required interfaces can be costly and error-prone. The problem is compounded in the case of services that do not follow simple request-response interactions, but instead engage in conversations comprising arbitrary patterns of message exchanges. A key challenge in this setting is service mediation: the act of retrofitting existing services by intercepting, storing, transforming, and (re-)routing messages going into and out of these services so they can interact in ways not originally foreseen. This thesis addresses one aspect of service mediation, namely service interface adaptation. This problem arises when the interface that a service provides does not match the interface that it is expected to provide in a given interaction. Specifically, the thesis focuses on the reconciliation of mismatches between behavioural interfaces, that is, interfaces that capture ordering constraints between message exchanges. We develop three complementary proposals. Firstly, we propose a visual language for specifying adapters for conversational services. The language is based on a an algebra of operators that are composed to define links between provided-required interfaces. These expressions are fed into an execution engine that intercepts, buffers, transforms and forwards messages to enact the adapter specification. Secondly, we endow such adapter specifications with a formal semantics defined in terms of Petri nets. The formal semantics is used to statically check the correctness of adapter specifications. Finally, we propose an alternative approach to service interface adaptation that does not require hard-wired links between provided and required interfaces. This alternative approach is based on the definition of mapping rules between message types, and is embodied in an adaptation machine. The adaptation machine sits between pairs of services and manipulates the exchanged messages according to a repository of mapping rules. The adaptation machine is also able to detect deadlocks and information loss at runtime.