Interest based recommendations with argumentation

Abstract

Arguments play two important roles in day to day decisions. Namely, they help us to select one or more alternatives in the process of decision making as well as to justify a chosen alternative. Recommender systems are information filtering systems that recommend information items which are likely to be of interest to the user. Hence argumentation can be used to select the relevant items as well as to give explanations and justifications for the said recommendations. This study proposes an argument-based framework for generating autonomous Interest Based Recommendations (IBR). The goal of the proposed framework is to identify the essential features required to enable IBR using argumentation among autonomous agents. The use of argumentation allows enhancement of multi-agent recommender systems with inference abilities to present the deeper motives and reasoned suggestions. These suggestions can be easily accepted by the user only if a convincing case can be made by the recommender system. This would enable the recommender agent to reason beyond certain user preferences in order to generate interesting recommendations. The framework aims to identify and deduce arguments for beliefs, desires and intentions behind the generated recommendations and user preferences. Different types of conflicts amongst the agents and ways of resolving them are also discussed in the proposed approach. Enhancing recommendation technologies through the use of argumentation for generating interesting recommendations for its users is demonstrated with the help of a case study supported by experimental results and a worked example. © 2011 Asian Network for Scientific Information.