Opinion-Based Filtering through Trust

Recommender systems help users to identify particular items that best match their tastes or preferences. When we apply the agent theory to this domain, a standard centralized recommender system becomes a distributed world of recommender agents. Therefore, due to the agent's world, a new information filtering method appears: the opinion-based filtering method. Its main idea is to consider other agents as personal entities which you can rely on or not. Recommender agents can ask their reliable friends for an opinion about a particular item and filter large sets of items based on it. Reliability is expressed through a trust value with which each agent labels its neighbors. Thus, the opinion-based filtering method needs a model of trust in the collaborative world. The model proposed emphasizes proactiveness since the agent looks for other agents in a situation of lack of information instead of remaining passive or providing either a negative or empty answer to the user. Finally, our social model of trust exploits interactiveness while preserving privacy.

[1]  Natalie S. Glance,et al.  Knowledge Pump: Supporting the Flow and Use of Knowledge , 1998 .

[2]  Jordi Sabater-Mir,et al.  REGRET: reputation in gregarious societies , 2001, AGENTS '01.

[3]  Matthias Klusch,et al.  Information agent technology for the Internet: A survey , 2001, Data Knowl. Eng..

[4]  Ronald R. Yager,et al.  On ordered weighted averaging aggregation operators in multicriteria decision-making , 1988 .

[5]  C. Sierra,et al.  REGRET: A reputation model for gregarious societies , 2001 .

[6]  Josep Lluís de la Rosa i Esteva,et al.  Developing trust in recommender agents , 2002, AAMAS '02.

[7]  V. Torra.  On the integration of numerical information: from the arithmetic mean to fuzzy integrals , 2004 .

[8]  Vicente Torra Ferré.  On the learning of weights in some aggregation operators: the weighted mean and OWA operators , 1999 .

[9]  M. Schillo,et al.  Who can you trust: Dealing with Deception , 1999 .

[10]  Cristiano Castelfranchi.  Information Agents: The Social Nature of Information and the Role of Trust , 2001, CIA.

[11]  D. Collard,et al.  Trust : making and breaking cooperative relations , 1989 .

[12]  Stephen Marsh,et al.  Formalising Trust as a Computational Concept , 1994 .

[13]  Michael Rovatsos,et al.  Using trust for detecting deceitful agents in artificial societies , 2000, Appl. Artif. Intell..

[14]  Rino Falcone,et al.  Principles of trust for MAS: cognitive anatomy, social importance, and quantification , 1998, Proceedings International Conference on Multi Agent Systems (Cat. No.98EX160).

[15]  Munindar P. Singh,et al.  A Social Mechanism of Reputation Management in Electronic Communities , 2000, CIA.

[16]  Diego Gambetta.  Can We Trust Trust , 2000 .

[17]  Luc Steels,et al.  Grounding adaptive language games in robotic agents , 1997 .

[18]  C. Badcock,et al.  Trust : making and breaking cooperative relations , 1989 .

[19]  G. Elofson.  Developing Trust with Intelligent Agents: An Exploratory Study , 2001 .

[20]  Josep Lluís de la Rosa i Esteva,et al.  A Taxonomy of Recommender Agents on the Internet , 2003, Artificial Intelligence Review.

[21]  Ronald R. Yager,et al.  On ordered weighted averaging aggregation operators in multicriteria decisionmaking , 1988, IEEE Trans. Syst. Man Cybern..

[22]  Vicenc Torra,et al.  Information Fusion in Data Mining , 2003 .

[23]  V. Torra.  On the learning of weights in some aggregation operators : the weighted mean and OWA operators , 1998 .