隨著社群網路的蓬勃發展，人與人或人與組織間的溝通模式也有很大的轉變，也使得消費者更願意主動於網路上，分享其所消費商品有關的各種經驗及評價。這些網路消費資訊對消費者及廠商都是具有很高參考價值，但因資料繁多及成長快速且具有時效性，往往需投入大量人力及時間進行分析，本實驗室已研發設計出一中文意見探勘系統解決此問題，也能提供更正確客觀之意見判斷。但於實務使用時，發現因缺少了自動排程功能及負面意見即時監控功能，無法得到最新評論資料的即時分析；因此本研究加入此功能，使系統可自動啟動收集文章並利用現有詞庫進行分析，能即時獲得初步分析結果，如遇重大事件發生時，也能即時對負面意見進行追蹤管理。本研究也將對演算法及報表功能進行修正及補強，以提升文章分析之準確度及避免報表查詢結果失真。 With the rapid development of social networks, communication patterns between people or between people and organizations have undergone major changes, making consumers more willing to share their consumer goods related experiences and evaluations through the Internet. Online consumer information has a very high reference value for consumers and vendors. However, due to the large quantity, rapid growth, and timeliness of data, a large amount of manpower input and time is often needed to carry out analysis. This laboratory has developed a Chinese opinion mining system to solve this problem, at the same time providing more objective opinions and judgment. Nevertheless, it was found through practical use that it lacked the features of automatic scheduling and real-time monitoring of negative comments, making it unable to obtain real-time analysis of the latest comments. Hence, these features were added in this research in order to enable the system to automatically start article collection and engage in analysis through the existing thesaurus, thereby deriving at preliminary analysis results and instantly tracking and managing negative opinions when major events occur. In this study, the algorithm and report functions were also corrected and reinforced in order to improve the accuracy of article analyses and avoid distortion of report query results.
