earticle

영어

In order to provide personalized knowledge recommendation services, most web portals for organizational knowledge management use category or keyword information that portal users explicitly express interests in. However, it is usually difficult to collect correct preference data for all users with this approach, and, moreover, users' preferences may easily change over time, which results in outdated user profiles and impaired recommendation quality. In order to address this problem, this paper suggests knowledge recommendation methods for portals using user profiles that are automatically constructed from users' activities such as posting or uploading of articles and documents. The result of our experiment shows that the proposed method can provide equivalent performance with the manual category or keyword selection method.