近年來，隨著資訊科技的發達，越來越多的人開始接受和使用新科技來協助獲取理財相關資訊。同時，在網路上也開始出現大量的投資理財報導，提供大眾作為投資理財的參考。因此，如何更有效率的從大量的網路資源中，找到有價值且符合使用者需求的資訊，並進一步組織成有結構的知識，儼然成為重要的議題。本研究嘗試結合常見的統計方法以及文字探勘技術，進行本體論學習。經由過濾及轉化文字內容的過程，找出理財報導中所隱含的特徵及關聯，進而將這些知識轉換為本體論，使過多冗雜理財資訊，符合使用者需求，協助讀者整合冗雜之理財資訊，並提供管理者進行分析與決策的依據。本研究以文字探勘技術協助專家建置出簡單結構的理財報導本體論知識。

With the rapid development of information technology in recent years, an increasing number of people have begun to accept and use new technologies as a means to obtain financial information. At the same time, extraordinary amounts of investment and financial news have been produced on the internet, providing an overwhelming number of references for the public. Thus, the ability to extract valuable pieces of information that match user needs from a sea of online resources and then organize them into structural knowledge has become increasingly important. The present study combines commonly used statistical methods with text mining techniques to investigate this issue of ontology further. The characteristics of and relationships among various financial news items are derived through a process of filtering and transforming of text contents. Ontology is subsequently applied to the derived knowledge in order to meet user requirements by helping readers to integrate the overly lengthy and disorganized financial information and in order to provide management personnel with a basis for analysis and decision making. This research assists experts in establishing a simple, structured ontology study of financial news through text mining techniques.