摘要
臺灣天然災害像如颱風、水災及地震發生頻繁，若能在災害來臨前預先得知一些警訊；當災害來臨時，可能可以減少災害發生帶給人們的傷害。近年來，大數據以及網路情資蓬勃發展，本文試圖探討該項技術應用於防災的可行性。
本研究利用蒐集網路情資並彙整成資料庫系統並進行資料整理，所收集的資料分為PTT八卦版以及三大新聞網站（中時、聯合和蘋果）兩部分。為測試分析結果，本文選取三個代表性的事件作為案例分析，包括2016年02月著名的0206地震、桃園機場淹水以及08月的尼伯特颱風。分析過程中，運用結巴中文斷詞系統（Jieba）進行關鍵字的定義，並將統計之數據以Arima進行預測模擬分析，得到結果後再針對結果進行探討。
研究結果發現：1.社群情資確實可以反應災害情資訊息、2.地震因為規模較大，網路使用者均可感受其影響，提前反應情資的效果較佳，且PTT較一般新聞媒體理想、3.水災具有地預域性，一般新聞媒體較PTT理想、4.ARIMA可以大略地預估災情的趨勢，可以提前預測災情輿論的發展。

Natural disasters such as typhoons, floods and earthquakes occur frequently in Taiwan. A signal of warning in advance of the disaster is preferred since such message may help us reduce the damage. Big data from network intelligence resources flourishes in recent years. This research attempts to explore the feasibility of the technology that is used in disaster prevention.
The collected data are divided into PTT Gossiping and three news websites (China times、Udn news and Apple daily). In order to examine and analyze the collected data, three representative events were selected as case studies, including the disastrous earthquake on February 6th, 2016, flooding in Taiwan Taoyuan International Airport on June 2nd, 2016 and Typhoon Nepartak in July 8th, 2016
Jieba is used to define keywords and ARIMA is sued to build a model for predicting the collected data. Based on results found here, some observation are described as follows: 1. Both PTT Gossiping and NEWS websites reflect the occurrence of disaster correctly, 2. Because earthquake covers greater area compared to that of the flooding event occurred in airport, information from PTT Gossiping can reflect hazard event earlier, 3. On the hand, flooding only influences its nearby area, so the news websites can have an earlier response, 4.ARIMA is able to predict the degree of disaster discussion on the internet community network.

參考文獻
む1めCritical Questions For Big Data, Boyed and Crawford 2012
む2めBig Data, Manovich 2011
む3めO. Zik, “Examining the Gap between Big Data and Environmental Sustainability Measurement”, Environmental Leader.〔Online〕.
む4めHadoop大數據處理，劉軍 2014
む5めSeeing Cities Through Big Data, Batty 2013. p274
む6め鉅量資料及其在農業生產上之應用潛力, 楊純明 2014
む7めBig Data, 麥爾荀伯格Viktor Mayer-Schonberger、庫基耶Kenneth Cukier 2013
む8め雲報專欄：量資料的技術發展與挑戰, 陳銘憲、林雨絜 2013
む9めData-Driven Innovation, ITF 2014
む10め1.台灣的自然環境與資源（上）。環境教育季刊 , 10,3-11。王鑫 1991
2.台灣的自然環境與資源（下）。環境教育季刊, 11,21-31。王鑫 1991
3.發展教師環境教育哲學之研究。國家科學委員會專題研究計劃成果報告。台北:行政院。王鑫、Steve Simpson、李淑媛 1994
む11め台灣颱風地形效應豪雨預警區之研究。博士 論文。台北:中國文化大學地學研究所。范銚燻 1999
む12め台灣地區的氣象災害與防災策略。 環境教育季 刊,41,38-48。陳正改 2000
む13め台灣的地形景觀與自然災害。環境教育季刊, p41。林俊全 2000
む14め國土及水資源保育。大專環境與永續發展教育通 識課程發展與教學計畫。線上檢索日期：民90年12月20日。網址: http://www.giee.ntnu.edu.tw/。趙振平 2001
む15め編號第 16 號第 39 報,海上陸上颱風警報 。
線上檢索日期:民 90 年 10 月 20 日。
網址:http://www.cwb.gov.tw/ 中央氣象局 2001
む16め營建工程防災技術, 沈茂松 2010
む17め臺灣地區各縣市災害防救能力評估之研究, 廖威彥 2002-2007
む18め“Word Segmentation through Constraint Satisfaction and Statistical Optimization.” Proceedings of ROCLING, 1991,pp. 147-165. Chang, J.S., et al. 1991
む19め“Word Identification for Mandarin Chinese Sen- tences,” Proceeding of COLING-92, 14th Int. Conf. On Computational Linguistics, pp. 101-107, 1992. Chen K. J. And S. H. Liu, (1992).

む20め“Statistical Models for Word Segmentation and Unknown Word Resolution.” Proceedings of ROCLING, 1992, pp. 121-146. Chiang, T.H.,et al. 1992
む21め“Automatic Word Identification in Chinese Sen- tences by the Relaxation Technique,” Computer Processing of Chinese and Oriental Languages, Vol. 2, No. 4, pp. 33-56, 1988. 
 Fan, C. K. and W. H. Tsai, (1988).
む22め“A Statistical Method for Finding Word Boundaries in Chinese Text,” Computer Processing of Chinese and Oriental Languages, Vol. 4,No. 4, pp. 336-351, 1990. 
 Sporat, R. and C. Shih,(1990).
む23め“Rule-Based Word Identification for Mandarin Chinese Sentences-A Unification Approach,” Computer Processing of Chinese and Oriental Languages, Vol. 5, No. 2, pp. 97-118, 1991. Yeh, C. L. and H. J. Lee,(1991)

む24め“Description of the NTU System Used for MET2,” Proceedings of 7th Message Understanding Conference (MUC-7), Chen, Hsin-Hsi, Yung-Wei Ding, Shih-Chung Tsai and Guo-Wei Bian 1998 http://www.itl.nist.gov/iaui/894.02/related_projects/muc/index.html.
む25め“中文辭彙歧義之研究-斷詞與詞性標示”, 第六屆中華民 國計算語言學研討會論文集 (ROCLING-6), pp. 173-194. 彭載衍、張俊盛 1993
む26め“Improved Source-Channel Models for Chinese Word Segmentation,” Proceedings of the 41st Annual Meeting on Association for Computational Linguistics (ACL 2003), pp. 272-279. Gao, Jianfeng, Mu Li, and Chang-Ning Huang 2003
む27め“Word segmentation in sentence analysis,” Proceedings of the 1998 International Conference on Chinese Information Processing, pp. 169-180. Wu, Andi and Jiang, Zixin 1998
む28め“A Class-based Language Model Approach to Chinese Named Entity Identification,” International Journal of Computational Linguistics and Chinese Language Processing, Vol 8, No 2, pp. 1-28. Sun, Jian, Ming Zhou, and Jian-Feng Gao 2003
む29 “Combining machine learning with linguistic heuristics for Chinese word segmentation,” FLAIRS Conference, pp. 241-246. Lu, Xiaofei 2007
む30め “An improved chinese word segmentation system with conditional random field,” Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing, pp. 162-165. Zhao, Hai, Chang-Ning Huang, and Mu Li 2006
む31め結合多類型字典與條件隨機域之中文斷詞與詞性標記系統研究, 台灣大學, 碩士論文。羅永聖 2008
む32め中央研究院中文計算語言研究小組,中文詞知識庫小組，網址：http://godel.iis.sinica.edu.tw/CKIP/。 

む33め如何使用JIEBA結巴中文分詞程式, 林志傑 2014，網址：http://blog.fukuball.com/ru-he-shi-yong-jieba-jie-ba-zhong-wen-fen-ci-cheng-shi/
む34め “MUC-7 Named Entity Task Definition, Version 3.5 ”, September 1997, http://www.muc.saic.com/ Chinchor, Nancy A 1997
む35め利用網路口碑推測墾丁國家公園旅遊市場溫度，國立臺東大學文化資源與休閒產業學系，蔡柏緯 2014
む36め利用網路訊息推測旅遊溫泉渡假遊客量之研究-某鄉村地區A度假村為例，施孟隆 2013
む37め谷歌尋引擎與台灣股市交易活動之關聯性，國立高雄第一科技大學金融所理財組，陳怡靜 2014
む38め運用搜尋引擎記錄黨與機器學習模型於傳染病監測之研究，國立台灣大學資訊管理學研究所，方澤翰 2010
む39めDetecting influenza epidemics using search engine query data. Nature, pages 1012-1015. 
 Ginsberg, J., Mohebbi, M.H., Patel, R.S., Brammer, L., Smolinski, M.S., and Brilliant, L. 2009. 

rm4xu;4y xulll