An interactive agent system for supporting knowledge-based recommendation: a case study on an e-novel recommender system

  • Authors:
  • Zeng-Wei Hong;Rui-Tang Huang;Kai-Yi Chin;Chia-Chi Yen;Jim-Min Lin

  • Affiliations:
  • Asia University, Taichung, Taiwan;Feng Chia University, Taichung, Taiwan;Feng Chia University, Taichung, Taiwan;Feng Chia University, Taichung, Taiwan;Feng Chia University, Taichung, Taiwan

  • Venue:
  • Proceedings of the 4th International Conference on Uniquitous Information Management and Communication
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

With the fast development of e-commerce, a large number variety of information existed on the Internet. Many researches tend to design a recommender system for assisting users to search the information that they have interested over the internet. The knowledge-based recommendation is one of solutions to guide the users to provide their needs, and further create a user preference model. In the past, agents commonly played the role of information retriever in a recommender system. Agents have the capability of autonomy and cooperation to assist in collecting the users' profiles and analyzing users' preferences. However, few of researches adopted embodied conversational agents (ECAs) to interact with users. In this study, we design an interactive agent system to support the knowledge-based recommendation. In addition to recommend products by using the knowledge from users' profiles, the knowledge-based approach also emphasizes the system should explain the cause of the recommendation result. For this reason, this study used ECAs to promote and explain recommendation results. As a result, our proposed system could reach the purpose of advertising products and receiving user feedbacks. In this paper, to demonstrate the usability of our system, we implement the interactive agent system in an e-novel web site, called Angel City, for recommending e-novels to readers.