Abstract. Recommendation systems have proven to be useful in various application domains. However, current solutions are usually ad-hoc systems which are tightly-coupled with the application domain. We present the IC-Service, a recommendation service that can be included in any system in a loosely coupled way. The implementation follows the principles of service oriented computing and provides a solution to various problems arising in recommendation systems, e.g. to the problem of meta-recommendation systems development. Moreover, when properly configured, the IC-Service can be used by different applications (clients), and several independent instances of the IC-Service can collaborate to produce better recommendations. Service architecture and communication protocols are presented. The paper describes also ongoing work and applications based on the IC-Service. 1

It is very di#cult for beginners to define and find the most relevant literature in a research field. They can search on the web or look at the most important journals and conference proceedings, but it would be much better to receive suggestions directly from experts of the field. Unfortunately, this is not always possible and systems like CiteSeer and GoogleScholar become extremely useful for beginners (and not only). In this paper, we present an agent-based system that facilitates scientific publications search. Users interacting with their personal agents produce a transfer of knowledge about relevant publications from experts to beginners. Each personal agent observes how publications are used and induces behavioral patterns that are used to create more e#ective recommendations. Feedback exchange allows agents to share their knowledge and virtual communities of cloned experts can be created to support novice users. We present a set of experimental results, obtained using CiteSeer as a source of information, that show the e#ectiveness of our approach.

People tend to form social networks within geographical areas. This can be explained by the fact that generally geographical localities correspond to common interests (e.g. students located in a university could be interested to buy or sell textbooks adopted for a specific course, to share notes, or just to meet together to play basketball). Cellular phones and more in general mobile devices are currently widely used and represent a big opportunity to support social communities. In this paper, we present a general architecture for multi-agent systems accessible via mobile devices (cellular phones and PDAs), where Bluetooth technology has been adopted to reflect users locality. We illustrate ToothAgent, an implemented prototype of the proposed architecture, and discuss the opportunities offered by the system.

Abstract. Cultural differences play a very important role in matching computer interfaces to the expectations of users from different national and cultural backgrounds. But to date, there has been little systematic research as to the extent of such differences, and how to produce software that automatically takes into account these differences. We are studying these issues using a unique resource: Common Sense knowledge bases in different languages. Our research points out that this kind of knowledge can help computer systems to consider cultural differences. We describe our experiences with knowledge bases containing thousands of sentences describing people and everyday activities, collected from volunteer Web contributors in three different cultures: Brazil, Mexico and the USA, and software which automatically searches for cultural differences amongst the three cultures, alerting the user to potential differences. 1.

Abstract—Rideshare systems allow a substantial number of people to mutually benefit from using less cars in a specific region. This would rationalize energy consumption, save money, and decrease traffic jams and pollution. However, accessibility issues have prevented these architectures from being widely spread. In this paper, we present an agent-based Rideshare system that is accessible via lightweight devices. We use auction mechanism as a method of negotiation among autonomous and proactive agents, by this we aim at accelerating agents ’ interactions while resolving end-user composite tasks. I.

Abstract. Web Service (WS) discovery is a critical problem hindering web service technology proliferation. The current solution, based on catalog-style browsing, provides no control over the quality of registered services. Application of matching techniques for WS retrieval is still under investigation. The objective of this work is the design of a framework to improve WS discovery. Our approach is based on application of distributed recommendation system to provide Quality of Service (QoS) information and on testing of retrieval methods on service specifications. 1

As Internet contains more pages, it becomes harder to find relevant information. Search engines aim at facilitating search process. However, they have shortcomings such as the lack of personalization. Recommendation systems are intended to exploit the fact that sometimes different users expect different answers to the same query. A recommendation system accepts queries from a user and exploits knowledge about his/her needs, behavior patterns search profiles and content information in order to make personalized suggestions. Such systems implement either content-based approach (e.g. using TF-IDF vectors [1]), either collaborative filtering [2], or combination of the both approaches. Producing personalized recommendations, these systems overcome the drawback of search engines. We present a multi-agent recommendation system Implicit for web search. Recommendation creation process is based on the concepts of Implicit Culture [3], namely on using implicit knowledge of the community members to help a newcomer to behave similarly to the other community members without

Botnets have yet to be exploited to their full potential, because they have yet to take advantage of all the information available to them. The zombie computers that comprise a botnet have access to the private documents of the people that use the computers. A botmaster who controls the botnet can harvest the documents and sell them to third parties, creating a viable – if illegal – online business. We outline motivations for such a business model, as well as the mechanics of a possible implementation. We then present a variety of defenses against this scenario. 1

Abstract. Very often people tend to behave as other people behaved previously. This happens in many different situations, for instance when one has to choose the path in a forest or when she/he has to select a link in the web. Social Navigation aims at providing assistance in such situations supporting the decision making process. Implicit Culture is a recent approach in which people are encouraged (induced) to behave according to usual behavior of the community. This paper shows similarities between Social Navigation and Implicit Culture and it presents a case study about user preferences learning. 1

multi-agent system, information agents Design patterns represent solutions to problems that have been proved to be useful in different contexts and can be reused. An experienced programmer can choose a suitable pattern for a given problem effectively. However, for an inexperienced programmer this is a very hard task. We propose a multi-agent system that supports programmers in choosing the design pattern suitable for the given problem. Personal agents in our system produce knowledge transfer among users, allowing for the reuse of experience in choosing design patterns.