隨著網際網路的普及化及消費者習慣的改變，現今消費者可以經由網路上各討論區或論壇來閱讀網友們的使用心得及詢問網友們的經驗或其意見，這種即時互動訊息所得到的結果，有非常大的機率左右消費者的決定，倘若能將這些網路上的口碑做追蹤及量化，相信這些訊息會重新定位業者在審核行銷效益的觀念。這項研究是經由使用探勘技術分析網絡論壇輿論，其目的為1.將四個影響客戶汽車購買決策之面向，二手、新車、服務、保養維修等主要考慮因素預先定義且推導並得出結論。2.車商可針對負向評價做長期性的追蹤，使其更加了解消費者的需求，提供改善的進步方向。我們收集並下載從汽車論壇Mobile01網站包含關鍵字“Toyota”的討論，將評論文章匯入至中文意見探勘系統，該系統就可以分析及產出基於四個面向的正面和負面評價成果之表格與圖表。該結果可以使用在無論是作為客戶汽車購買決策的一個參考資料，或提供給車商在製造銷售策略和產品/服務改進的重要資訊。 Along with the popularization of Internet and the change of consumer habits, consumers can now read the articles of product review posted in discussion forum by people in Internet and query their use experiences or opinions. The result from these online and interactive messages is very likely to change the consumer’s decision. If these public praise could be tracked and quantified effectively, it will reset the concept to evaluate the efficiency of marketing activities for industry. This research is to analyze the public opinions in Internet forums by using data mining technology. The purposes are listed below: 1. There are four features to affect consumers to choose their car: new car, used car, customer service and car maintenance. This research will get the final conclusion by giving the accurate definition and deduction for these four features. 2. Car manufacturer could have better understanding of consumer need and the direction of improvement by the long-term trace of the negative criticism. We collected and downloaded the posts that include the keyword ‘Toyota’ from the car forum in Mobile01 (www.mobile01.com) and import these comments into the Chinese data mining system. This system will analyze these data based on the four factors mentioned before and output the positive and negative results to tables and charts. These results are very important reference for both the consumers to choose their car and the car manufacturers to build their marketing strategy and improve their customer service.