民眾愈來愈依賴日常運作的運輸系統，亦習慣於社群媒體網路平台發表與 分享使用交通運輸系統之經驗，若能針對民眾網路意見進行有效的輿情分析， 則有助於管理者即時掌握熱門議題而擬訂對應的處理措施。本研究將社群運算 應用於交通輿情情感傾向分析，藉由文獻彙整與專家討論歸納一包含文本蒐集、 文本處理、文本分類、情感分析步驟之網路輿情情感傾向分析模式，並將其應 用於國道電子收費政策議題上，期望藉由此模式對我國實施計程收費政策後之 網路意見進行文本挖掘，並瞭解民眾網路討論話題之情感傾向趨勢。本研究首 先撰寫爬蟲系統程式，對網路評論文本進行蒐集與處理，再運用WEKA 軟體進 行文本分類，以此作為情感傾向分析之依據。本研究建構之網路輿情情感傾向 分析模式與流程，除可作為未來自動化網路輿情分析系統之雛型之外，亦可應 用於其他相關熱門話題。

The degree of relying on daily transportation systems is more and more significant for Taiwan’s people. Owing to ubiquitous Internet technologies, they get used to share and express their viewpoints on experiencing transportation systems via social media platforms. If managers can obtain these real-time public opinions, corresponding strategies can be provided effectively. The approach applying social computing to sentiment orientation analysis of Internet public opinions in this study consists of text gathering, processing, classifying and sentiment analyzing. An empirical study on Internet public opinions and sentiment orientation analysis of distance-based Electronic Toll Collection on Taiwan’s Freeway is conducted. With the help of web crawler systems, ETC related texts are firstly gathered and processed. Then WEKA software is used for text classifications and further applications. Features and sentiment words are constructed as fundamentals for text classification and sentiment orientation analysis. The approach in this study can be not only as a prototype for developing automatic Internet public opinions analysis systems, but also applied to other hot topics.