A Novel Group Recommendation Based on Knowledge Flows

In a knowledge-intensive environment, a task in an organization is typically performed by a group of people who have task-related knowledge and expertise. Document recommendation methods are very useful to resolve the information overload problem and proactively support knowledge workers in the performance of tasks by recommending appropriate documents to meet their information needs. A worker's document referencing behavior can be modeled as a knowledge flow (KF) to represent the evolution of his/her information needs over time. However, the information needs of workers and groups may change over time. Additionally, most traditional recommendation methods which provide personalized recommendations do not consider workers' KFs, or the information needs of the majority of workers in a group to recommend task knowledge. In this work, the group-based collaborative filtering (GCF) method which integrates the KF mining method is proposed to actively provide task-related documents for groups. Experimental results show that the proposed method has better performance than the personalized recommendation methods in recommending the needed documents for groups. The proposed method can fulfill the groups' task needs and facilitate the knowledge sharing among groups.