當一般民眾為瞭解一重大事件之發展脈絡時，其往往藉由網際網路搜尋是否存在該事件對應之「懶人包」可參考並理解該事件之相關資訊。若無此類事件對應之「懶人包」可供參考，其往往透過各類管道蒐集、閱讀該事件之相關文件/新聞內容，以期掌握該事件之全貌及重點資訊；然而，由於民眾未必可於網際網路尋得各事件對應之「懶人包」，導致其於蒐集與該事件具關聯性之文件/新聞內容時需花費大量時間釐清此些文件/新聞內容，方可掌握事件的關鍵資訊與整體發展脈絡。
為解決上述問題，本研究乃先自各類管道蒐集多個現行重大事件之相關文件/新聞內容，並解析此些文件/新聞內容所包含之特徵且歸納各特徵之表達結構及表達類型。之
後，本研究乃以前述解析結果為基礎發展「文件/新聞內容關鍵資訊整合」方法論，此方法可針對各事件文件/新聞內容進行特徵擷取；其次，此方法以K-平均分群方法將所有事件文件/新聞區分為多個不同時間區段之事件文件/新聞群集；而後，此方法乃利用餘弦相似性計算各事件文件/新聞群集中兩兩事件文件/新聞內容的相似度，並從中判定各事件文件/新聞群集中與其他事件文件/新聞內容具較高共通性之事件文件/新聞內容；最後，此方法乃將各事件文件/新聞群集中與其他事件文件/新聞內容具較高共通性之事件文件/新聞內容所包含的事件重點資訊以視覺化方式呈現，以協助一般民眾縮短釐清眾多文件/新聞內容之時間，進而快速且有效掌握事件之全貌及整體發展過程。

As people are interested in the development of a major event, they usually search for the “a short version of related major event” through the Internet. If there isn’t such thing as “a short version of related major event” for reference, they have to collect and organize the relevant documents/news content of the event through various channels. However, people may not finding the “a short version of related major event” corresponding to each event on the Internet, Therefore, people have to spend time in clarify the documents/news content to grasp the key event information and overall development. In order to solve the above problems, this research develops a model that can be used to integrate and visualize the key of major event information
and overall development process.

摘要.................................................I
ABSTRACT............................................II
目錄................................................III
圖目錄................................................V
表目錄..............................................VII
第一章、研究背景.......................................1
第二章、文獻回顧......................................12
第三章、以文件內容為基礎之重大事件綜合性摘要分析模式 .... 22
第四章、績效驗證與分析............................... 140
第五章、結論與未來展望............................... 173
參考文獻 ........................................... 178
附錄A、模式驗證資料 ................................. 180
附錄B、模式於第二階段績效驗證結果 ... ................. 301
附錄C、「文件/新聞內容關鍵資訊整合及視覺化」議題之問卷 .. 362

1. Li, Y.-R., Wang, L.-H. and Hong, C.-F., 2009, “Extracting the Significant-Rare Keywords for Patent Analysis,” Expert Systems with Applications, Vol. 36, pp. 5200-5204.
2. Seon Joo Kim., Fanbo Deng. and Michael S.Brown.,2011, “Visual enhancement of old documents with hyperspectral imaging,” Proceedings of the 2011 Pattern Recognition Volume44 Issue7, pp. 1461-1469.
3. Stoffel, F., Jackle, D. and Keim, D., 2014, “Enhanced News-Reading: Interactive and Visual Integration of Social Media Information,” Proceedings of the 9th International Conference
on Language Resources and Evaluation (LREC), pp. 21-28.
4. Noda, S. and Fujita, K., 2015, “Trend Extraction Method using Co-occurrence Patterns from Tweets,” Proceedings of the 2015 IIAI 4th International Congress on Advanced Applied Informatics, pp. 629-632.
5. Han, Y., Wang, G., Yu, J., Liu, C., Zhang, Z. and Zhu, M., 2016, “A Service-Based Approach to Traffic Sensor Data Integration and Analysis to Support Community-Wide Green Commute in China,” IEEE Transactions on Intelligent Transportation Systems, Vol. 17, pp. 2648-2657.
6. Yu Su., Quanming Yao and Huamin Qu., 2017, “VISTopic : A visual analytics system for making sense of large document collections using hierarchical topic modeling,” Proceedings of the 2017 Visual Informatics Volum1 Issue1, pp. 40-47.
7. Xueming Wang., Zechao Li. and Jinhui Tang.,2017, “Multimedia news QA: Extraction and visualization integration with multiple-source information,” Proceedings of the 2017 Image and Vision Computing, pp. 162-170.
8. Yu Su. and Jen-Chu Liu., 2019, “The Research of Data Visualization for the Web,” Proceedings of the 2019 Chinese Association of Graphics Science & Technology, pp. 215-234.
9. Sara Zhalehpour., Ehsan Arabnejad., Chad Wellmon., Andrew Piper. and Mohamed Cheriet., 2019, “Visual information retrieval from historical document images,” Proceedings of the 2019 Journal of Cultural Heritage, pp. 14-28.