個人文件夾組織環境之文件推薦研究

Abstract

知識分享是企業組織進行知識管理以保持競爭力之重要活動。在組織中，知識工作者通常會建構個人文件夾來儲存與整理知識文件。在個人文件夾的組織環境中，如何分析其他同儕文件夾的知識文件，以提供知識工作者所需知識文件，進而達到知識分享為一重要的研究議題。推薦機制已經成功的應用在推薦產品或是電影，本研究運用推薦技術從他人文件夾選取知識文件，以推薦知識工作者所需文件至其個人文件夾。本研究提出了以內容為基礎之過濾、合作式過慮與混合式過慮方法，並且進行實驗以驗證各個方法之推薦品質。實驗結果顯示出混合式推薦方法優於其他方法。

Sharing sustainable and valuable knowledge among knowledge workers is a prominent activity of knowledge management. In organizations, knowledge workers usually have their own personal folders that store and organize needed codified knowledge (textual documents) in taxonomy. In such personal folder environments, providing knowledge workers needed knowledge from other workers’ folders is important to facilitate knowledge sharing. Recommendation techniques have been successfully used in various applications to recommend items such as movies and products to individual user. This work adopts recommendation techniques to provide knowledge workers needed textual documents from other workers folders. Several approaches have been investigated and proposed, including content-based filtering, collaborative filtering and hybrid approaches for recommending textual documents in personal folder environments. Experiments are conducted to verify the performance of various methods using data collected from a research institute laboratory. The experimental result shows that the hybrid approach outperforms other methods.