Multi-agent matchmaking

Foner, Leonard N.; Crabtree, I. B.

doi:10.1007/3-540-62560-7_40

Cited by 17 publications

(12 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Systems exist that can simplify some of this vital work via human and agent recommendations. For examples of such systems, see Kuokka and Harada (1995), Foner and Crabtree (1996), Marsh and Masrour (1997), and the proceedings of the annual conference on Cooperative Information Agents (Kandzia & Klusch, 1997; Klusch & Kerschberg, 2000; Klusch, Shehory, & Weiss, 1999; Klusch & Weiss, 1998; Klusch & Zambonelli, 2001). Clearly, here, trust in the human or agent making the recommendation is of paramount importance and is related to our first level of trust in technology.…”

Section: Trust In Information Science and Technologymentioning

confidence: 99%

The role of trust in information science and technology

Marsh

Dibben

2003

Annual Review Info Sci & Tec

149

View full text Add to dashboard Cite

IntroductionThis chapter discusses the notion of trust as it relates to information science and technology, specifically user interfaces, autonomous agents, and information systems. We first present a n in-depth discussion of the concept of trust in and of itself, moving on to applications and considerations of trust in relation to information technologies. We consider trust from a "soft" perspective-thus, although security concepts such as cryptography, virus protection, authentication, and so forth reinforce (or damage) the feelings of trust we may have in a system, they are not themselves constitutive of ''trust." We discuss information technology from a human-centric viewpoint, where trust is a less well-structured but much more powerful phenomenon.With the proliferation of electronic commerce (e-commerce) and the World Wide Web (WWW, or Web), much has been made of the ability of individuals to explore the vast quantities of information available to them, to purchase goods (as diverse as vacations and cars) online, and to publish information on their personal Web sites. Now that the hyperbole 465 466 Annual Review of Information Science and Technology has died down somewhat and the situation is beginning to stabilize, we wish to examine one of the more important aspects of this "information revolution": the concept of trust. Although always simmering in the background of the social sciences literature, especially over the past decade in management, the study of trust has moved center stage in the world of online information and direct interaction (see, for example, Marsh, Meech, & Dabbour, 2000;Palmer, Bailey, & Faraj, 2000; Rosenbloom, 2000b;Urban, Sultan, & Qualls 1999).Thus, a n understanding of trust's role and impact is crucial for information systems practitioners and researchers; the main purpose of this review is to provide such a n understanding. The chapter is primarily aimed at management scientists with a n interest in social informatics, designers with a n interest in social phenomena, and other similar readers. However, they will be disappointed if they expect a study of a broad range of social interactionist influences, such as social capital (e.g., Lesser, 2000), authenticity and credibility (e.g., Council on Library and Information Resources, 20001, authority (e.g., Wilson, 19831, knowledge management (e.g., Davenport & Cronin, 20001, and communities of practice (e.g., Prusak & Cohen, 2000;Wenger, 1998Wenger, ,2000, to name but a few. Each of these has a quite separate theoretical base, even if they appear ostensibly similar to the lay reader; a review encompassing such a broad range of influences is beyond our scope.Trust has been the topic of considerable study in the social sciences for many years. As such, the chapter consists of a number of sections designed to enable the reader to acquire (1) a broader understanding of how trust operates as a social and interactional phenomenon and, based on this, (2) a more specific understanding of where trust fits into research and practice in inf...

show abstract

Section: Trust In Information Science and Technologymentioning

confidence: 99%

The role of trust in information science and technology

Marsh

Dibben

2003

Annual Review Info Sci & Tec

149

View full text Add to dashboard Cite

show abstract

“…• If multiple users of the system have similar interests, agents can exploit user profile information to make them aware of one another [6].…”

Section: The Role Of Agents In the Virtual Laboratorymentioning

confidence: 99%

“…This information is derived from each user's profile, and is used in a number of ways. A close match between the interests of two users indicates that they may profit from collaboration (a match-making task [6]). Additionally, if there exists a user with a broader range of interests than another, then those wider interests may be suggested to the PAA of the other user (a collaborative filtering task [13]).…”

Section: Mediatorsmentioning

confidence: 99%

Constructing a virtual training laboratory using intelligent agents

Norman¹,

Jennings²

2002

IJCEELL

View full text Add to dashboard Cite

This paper reports on the results and experiences of the Trilogy project; a collaborative project concerned with the development of a virtual research laboratory using intelligent agents. This laboratory is designed to support the training of research students in telecommunications traffic engineering.Training research students involves a number of basic activities. They may seek guidance from, or exchange ideas with, more experienced colleagues. High quality academic papers, books and research reports provide a sound basis for developing and maintaining a good understanding of an area of research. Experimental tools enable new ideas to be evaluated, and hypotheses tested. These three components-collaboration, information and experimentation-are central to any research activity, and a good training environment for research should integrate them in a seamless fashion. To this end, we describe the design and implementation of an agent-based virtual laboratory.

show abstract

“…These types of goals have been realized through the use of multiagent systems. Examples of such systems are the Kasbah framework for e-commerce [3], and matchmaking systems such as Yenta [4,5,6] and ACORN [8].…”

Section: Introductionmentioning

confidence: 99%

Just-in-time information sharing architectures in multiagent systems

Carter

Ghorbani

Marsh³

2002

Proceedings of the First International Joint Conference on Autonomous Agents and Multiagent Systems Part 2 - AAMAS '02

View full text Add to dashboard Cite

ACORN (Agent-based Community Oriented Routing Network) is a distributed multi-agent architecture for the search, distribution and management of information across networks. ACORN utilises the concept of 'information as agent' together with an application of Stanley Milgram's Small World Problem (the idea of the Six Degrees of Separation) in order to route individual items of information around a network of people and agents. This paper describes additions made to the ACORN architecture and the implementation. A directory server that facilitates real-time communication between a client and corresponding agent is implemented. This server allows for instant feedback and modification to the agent by the client. The concept of an anonymous service provider is introduced to allow clients to generate anonymous agents that cannot be traced back to the original creator of the agent. This service is vital for maintaining some privacy aspects of the user. ACORN consists of a set of information-sharing locations referred to as Cafés. A dynamic café clustering method is developed. Using the proposed clustering method, cafés are dynamically created / destroyed to most accurately reflect the collective interests of the given members of said café. The performance evaluation of the proposed structure for the café using a testbed of multiple virtual users shows that the addition of multi-café component to ACORN's architecture improves its information sharing efficiency and leads to significant reduction in unnecessary mingling. Lastly, the concept of a fat and thin agent is introduced. A fat/thin agent architecture allows for minimizing network traffic as agents traverse the network in search of or distribution of knowledge.

show abstract

Multi-agent matchmaking

Cited by 17 publications

References 3 publications

The role of trust in information science and technology

The role of trust in information science and technology

Constructing a virtual training laboratory using intelligent agents

Just-in-time information sharing architectures in multiagent systems

Contact Info

Product

Resources

About