i-Seek : an intelligent system for eliciting and explaining knowledge

We propose i-Seek, an Intelligent System for Eliciting and Explaining Knowledge that leverages the OpenMind [1] Commonsense knowledge base in conjunction with domain- specific knowledge in Personal Finance, Technical Help, and Health domains to act as an advisory system for novice users. Most of the interfaces are plagued by recurrent key problems: 1) elicitation - how to ask questions that enable the expert model to make decisions, and at the same time, are understandable to the novice, and 2) explanation - how to explain rationale behind expert decisions in terms that the user can understand. i- Seek maps the user's goals and expectations to the corresponding expert model's attributes as expressed in domain-specific terms. For example, instead of asking "What is your risk tolerance?", where the user might not comprehend the notion of risk tolerance, i-Seek tries to elicit the same information by asking a non-direct question such as "Do you usually buy lots of lottery tickets?". i-Seek constructs the novice user model by taking into account the user's personal information, interactions history, and the current context.

Department dc:contributor.department

Massachusetts Institute of Technology. Dept. of Architecture. Program In Media Arts and Sciences

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2005

Author dc:creator

• Kumar, Ashwani, S.M. Massachusetts Institute of Technology

Advisor dc:contributor.advisor

• Henry Lieberman.

• Architecture. Program In Media Arts and Sciences

Statement dc:rights

• M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

http://hdl.handle.net/1721.1/32523

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/32523