建構一個個人化的中文新聞代理人

Abstract

全球資訊網已成為一個可以將資訊散播到眾多使用者的有效方法了，越來越多的資訊和服務都可以線上取得。然而，也卻因資訊氾濫而急需一個有效的資訊過濾機制。許多的網站（例如CNN）針對這個問題，允許使用者能自定只包含自己有興趣的個人化網頁。在本論文中，我們將提出一個具有學習能力的個人化中文新聞代理人，並實作一個根據使用者個人設定檔(User Profile)制定而成之使用者導向瀏灠模組。當使用者與系統互動時，個人化的使用者設定檔將會在網站伺服端組成建立起來，而這些個人化資料將用來推薦適合的新聞給每一個使用者。

The World Wide Web has become a powerful means of disseminating information to users of unprecedented size. More and more information and services are offered on-line. However, the information overload on the web has created a great need for efficient filtering mechanisms. Many sites (e.g., CNN) address this problem by allowing a user to create personalized pages that contain only information that is of interest to the user. In this thesis, we proposed a personal Chinese news agent with learning capability. A user-oriented browsing model based on user profile, will be proposed and implemented. As users interact with the system, individual 'user profiles' are updated at the web server site. These are used to recommend the news to each user.