Behavior-based Preference Elicitation Method for Decision Support Systems

• Research unit: COST
• Project number: C07.0136

Key words (English)

Preference elicitation and modeling; recommender systems; eye-tracking system; decision behaviors in e-commerce

Research programs (English)

COST-Action IC0602 - Algorithmic Decision Theory

Short description (English)

To develop a flexible and interactive preference eliciation acquisition method based on users behaviors using emerging technologies such as eye-tracking systems.

Further information (English)

Full name of research-institution/enterprise: EPF Lausanne Human Computer Interaction Group, Faculty of Computer and Communication Sciences IC IIF GR-PU, BC 107

Partners and International Organizations (English)

AT, BE, CH, CY, DE, DK, ES, FI, FR, GR, HU, IE, IL, ITR, LT, LU, MK, NL, NO, PL, PT, RO, UK

Abstract (English)

Within the framework of this project, we aim at enhancing the theory around preference elicitation and modeling. This requires to better understand users' behaviors, and will lead to a significant improvement in the design of recommender algorithm. In order to reach this goal, we have initiated user studies relying on an explicit and implicit analysis of usage in an e-commerce application. Action logs, questionnaires and the use of an eye-tracking system helps us to identify the steps punctuating the purchase decision-making process. The results of these experiments allow us to develop new kind of recommender algorithms based on personality and temper, and providing diversity. A wine website will be used to validate these new models.

References in databases (English)

Swiss Database: COST-DB of the State Secretariat for Education and Research Hallwylstrasse 4 CH-3003 Berne, Switzerland Tel. [phone] Swiss Project-Number: C07.0136