Evaluation and Validation of a Conversational Agent Embodied in a Bookstore

This work presents an agent-based interface that is not merely reactive to some user request, but is proactive since it is capable of engaging in a goal-directed conversation with the user, e.g., by taking the initiative to recommend new products. The naturalness of interaction, especially for casual users, is enhanced by appropriate 2D facial models. The proactiveness of the agent is based on a recommendation engine that combines content-based retrieval, which exploits user profiles based on content features extracted from the dialogue and descriptions of items that users find relevant, with collaborative filtering, which clusters users according to their expressed taste to generate recommendations within these virtual communities. The proposed system has been evaluated and validated by using a top-down approach, focusing on the system/user interaction.

[1]  Floriana Esposito.  AI*IA 2001: Advances in Artificial Intelligence , 2001, Lecture Notes in Computer Science.

[2]  Ulrich Thiel,et al.  Helping conversational agents to find informative responses: query expansion methods for chatterbots , 2002, AAMAS '02.

[3]  Matthias Schneider-Hufschmidt,et al.  Adaptive User Interfaces: Principles and Practice , 1993 .

[4]  Fabio Abbattista,et al.  Learning Interaction Models in a Digital Library Service , 2001, User Modeling.

[5]  Amanda Spink,et al.  Real life, real users, and real needs: a study and analysis of user queries on the web , 2000, Inf. Process. Manag..

[6]  Amanda Spink,et al.  Interaction in information retrieval: selection and effectiveness of search terms , 1997 .

[7]  Nicola Fanizzi,et al.  Interaction Profiling in Digital Libraries through Learning Tools , 2000, ECDL.

[8]  Fabio Abbattista,et al.  User Profiling in an Application of Electronic Commerce , 2001, AI*IA.

[9]  Brian Stanford-Smith,et al.  E-work and E-commerce : novel solutions and practices for a global networked economy , 2001 .

[10]  Verner Andersen,et al.  Establishing criteria for evaluating intelligent agents in E-commerce , 2001 .

[11]  Hans H. K. Sønderstrup-Andersen,et al.  Evaluation of Agents and Study of End-user needs and behaviour for E-commerce: COGITO Focus group experiment , 2001 .

[12]  H.H.K. Andersen,et al.  Evaluation of the COGITO system , 2002 .

[13]  Martha E. Crosby,et al.  Introduction to the Special Issue on Empirical Evaluation of User Models and User Modeling Systems , 2004, User Modeling and User-Adapted Interaction.

[14]  David N. Chin.  Empirical Evaluation of User Models and User-Adapted Systems , 2001, User Modeling and User-Adapted Interaction.

[15]  Piotr J. Gmytrasiewicz,et al.  User Modeling 2001 , 2001, Lecture Notes in Computer Science.

[16]  Shimei Pan,et al.  Designing and Evaluating an Adaptive Spoken Dialogue System , 2002, User Modeling and User-Adapted Interaction.

[17]  Carol H. Fenichel,et al.  Online searching: Measures that discriminate among users with different types of experiences , 1981, J. Am. Soc. Inf. Sci..