Abstract. Multiuser museum interactives are computer systems installed in museums or galleries which allow several visitors to interact together with digital representations of artefacts and information from the museum's collection. In this paper, we describe WeCurate, a socio-technical system that supports co-browsing across multiple devices and enables groups of users to collaboratively curate a collection of images, through negotiation, collective decision making and voting. The engineering of such a system is challenging since it requires to address several problems such as: distributed workflow control, collective decision making and multiuser synchronous interactions. The system uses a peer-to-peer Electronic Institution (EI) to manage and execute a distributed curation workflow and models community interactions into scenes, where users engage in different social activities. Social interactions are enacted by intelligent agents that interface the users participating in the curation workflow with the EI infrastructure. The multiagent system supports collective decision making, representing the actions of the users within the EI, where the agents advocate and support the desires of their users e.g. aggregating opinions for deciding which images are interesting enough to be discussed, and proposing interactions and resolutions between disagreeing group members. Throughout the paper, we describe the enabling technologies of WeCurate, the peer-to-peer EI infrastructure, the agent collective decision making capabilities and the multi-modal interface. We present a system evaluation based on data collected from cultural exhibitions in which WeCurate was used as supporting multiuser interactive.

Abstract. This paper proposes a system that allows a group of human users to share their cultural experiences online, like buying together a gift from a museum or browsing simultaneously the collection of this museum. We show that such application involves two multiple criteria decision problems for choosing between different alternatives (e.g. possible gifts): one at the level of each user, and one at the level of the group for making joint decisions. The former is made manually by the users via the WeShare interface. This interface displays an image with tags reflecting some features (criteria) of the image. Each user expresses then his opinion by rating the image and each tag. A user may change his choices in light of a report provided by his WeShare agent on the opinion of the group. Joint decisions are made in an automatic way. We provide a negotiation protocol which shows how they are reached. Both types of decisions are based on the notion of argument which has a particular form. Indeed, a tag which is liked by a user constitutes an argument pro the corresponding image whereas a tag which is disliked gives birth to a cons argument. These arguments may have different strengths since a user may express to what extent he likes/dislikes a given tag. Finally, the opinion analysis performed by a WeShare agent consists of aggregating the arguments of the users.

This paper introduces the notion of experiences, which help situate agents in their environment, providing a concrete link on how the continually evolving environment impacts the evolution of an agent's BDI model. Then, using the notion of shared experience as a primitive construct, we develop a novel formal model of shared intention which we believe more adequately describes and motivates social behaviour than traditional BDI logics that focus on modelling individual agents. Whilst many philosophers have strongly argued that collective intentionality cannot always be equated to the collection of the individual agents, there has been no AI model that has proposed how this could occur. To the best of our knowledge this is the first attempt to develop the notion of shared experience from an AI perspective that cannot be reduced to descriptions of a single agent.