Automatic Conversation Driven by Uncertainty Reduction and Combination of Evidence for Recommendation Agents

Abstract.

We present an adaptive recommendation system named TalkMine, which is based on the combination of Evidence from different sources. It establishes a mechanism for automated conversation between recommendation agents, in order to gather the interests of individual users of web sites and digital libraries. This conversation process is enabled by measuring the uncertainty content of knowledge structures used to store evidence from different sources. TalkMine also leads different databases or websites to learn new and adapt existing keywords to the categories recognized by its communities of users. TalkMine s currently being implemented for the research library of the Los Alamos National Laboratory under the Active Recommendation Project

The process of identification of the interests of users relies on a process of combining several fuzzy sets into evidence sets, which models an ambiguous “and/or” linguistic expression. The interest of users is further fine-tuned by a human-machine conversation algorithm used for uncertainty reduction. Documents are retrieved according to the inferred user interests. Finally, the retrieval behavior of all users of the system is employed to adapt the knowledge bases of queried information resources. This adaptation allows information resources to respond well to the evolving expectations of users.

Keywords

Recommendation Systems, Information Retrieval, Web-related technologies, Fuzzy Set Theory, Evidence Sets, Measures of Uncertainty, Collaborative Systems, Adaptive Systems, Distributed Artificial Intelligence, Human-machine Interaction, Communities of Agents, Knowledge Representation, Soft Computing.

For the full paper please download the pdf version

For more information contact Luis Rocha at rocha@indiana.edu.
Last Modified: September 02, 2004