Examining the Relationships among User Involvement, Profile Quality, and Information Filtiring Performance

Abstract

Three major types of user profile acquisition modes employed in diverse filtering systems were identified: a rule-based user driven mode, an explicit-learning mode, and an implicit-learning mode. The main goal of this study was to clarify the influence of different levels of user involvement in these three profile acquisition modes and their impact on profile accuracy and filtering performance. Three versions of a filtering system utilizing the different acquisition modes and a baseline version without a profile acquisition mode were developed. Thirty-five students were recruited from the Indiana University and were randomly assigned to the four different types of systems (i.e., four experimental groups were formed). Results obtained from the four groups showed that different profile acquisition modes had varying impact on profile accuracy and filtering performance.