在網際網路蓬勃發展的現在，顛覆了過去的商業經營模式，也使得消費者搜集商品相關資訊的方法進而改變，對於口碑傳播也提供一種全新的管道，意即網站成為傳播的媒介，口碑訊息傳播打破了以往限制，提供消費者除了身邊親友之外，更多元的訊息來源。
本論文針對論壇Mobile 01的電信綜合討論區相關文章做資料分析，運用「中文意見探勘系統」進行實驗，藉由分析電信相關評論，系統所產生的分析結果，確定準確率、F1、回收率等實驗數據已達穩定。
最後，本研究的結果除了可以提供網路正負面口碑之分析參考，應用於商品相關之口碑行銷，也希望藉此提供給廠商，利用「中文意見探勘系統」中「異常評價分析」功能的輸出結果，讓廠商在面對網路負面口碑時，做為因應解決對策之參考。

With today’s flourishing Internet development, the past business model subverted, which in turn changed consumers’ way of collecting product-related information. Word-of-mouth dissemination provides a new pipeline, which means websites have become media of dissemination. Word-of-mouth dissemination has overcome limitations in the past to provide consumers more diverse information sources in addition to family and friends.
This paper targeted the data analysis of articles in the Mobile 01 Telecommunications General Discussion Area. Experiments were conducted using the “Chinese Opinion Mining System.” Through the analysis of telecommunications related remarks and the analysis results generated by the system, it was confirmed that the accuracy rate, F1, recovery rate, and other experimental data reached stability.
Finally, the results in this study shall serve as a reference for positive and negative Internet word-of-mouth, which can be applied in product related word-of–mouth. The “unusual evaluation and analysis” in the “Chinese Opinion Mining System” shall also be provided to companies to serve as a reference for them to devise coping strategies and solutions when faced with negative word-of-mouth.

目錄
第1章 緒論	1
1.1 研究動機與目的	1
1.2 論文架構	4
第2章 文獻探討	5
2.1 意見單元定義	5
2.2 意見探勘系統	9
2.3 口碑行銷	19
第3章 研究方法	22
3.1 問題陳述	22
3.2 系統設計	24
第4章 案例分析	35
4.1 評估方式與實驗結果	35
4.2 電信分析	41
4.3 異常評價分析	78
第5章 結論	87
參考文獻	88
附錄-英文論文	90

圖目錄
圖1   Opinion Observer的比較畫面	10
圖2   人工標註系統畫面	11
圖3   WebFountain GUI 經過意見分析後的產品比較圖	12
圖4   WebFountain可以讓使用者選擇產品以及來源，並且顯示出評論	12
圖5   ReMiner在手機上根據特徵分類(Common圖)	13
圖6   Special圖	14
圖7   Cloud圖	15
圖8   Categories圖	15
圖9   CopeOpi使用者選擇畫面	17
圖10  各個時間趨勢	17
圖11  包含主題的文章	17
圖12  可選擇有關的電影以及特徵，並且知道正負傾向評論等級	18
圖13  系統架構圖	24
圖14  演算法流程圖	26
圖15  系統統計分析示意圖	28
圖16  Topic分析報表流程圖	29
圖17  Feature/產品分析流程圖	31
圖18  異常評價分析流程圖	33
圖19  雷達圖分析流程	34
圖20  電信各月分準確率 2011-11~2012-06	37
圖21  電信各月分回收率 2011-11~2012-06	38
圖22  電信各月份F-1值 2011-11~2012-06	38
圖23  電信各月分準確率 2012-07~2013-02	39
圖24  電信各月份回收率 2012-07~2013-02	39
圖25  電信各月份F-1值 2012-07~2013-02	40
圖26  五大電信雷達圖2011-11~2013-02	42
圖27  五大電信業者討論文章數及所佔比例2011-11~2013-02	44
圖28  中華電信、遠傳、台灣大哥大Topic評價分析折線圖2011-11~2013-02	45
圖29  Feature/產品評價分析 收訊品質圓餅圖2011-11~2013-02	47
圖30  Feature/產品評價分析 收訊品質直條圖2011-11~2013-02	49
圖31  Feature/產品評價分析 威寶收訊品質折線圖2011-11~2013-02	50
圖32  威寶負評討論系統截圖	50
圖33  威寶2011-11~2013-02正面評價雷達圖	52
圖34  威寶2011-11~2013-02負面評價雷達圖	52
圖35  五大電信業者上網速度文章數及所佔比例2011-11~2013-02	55
圖36  Feature/產品評價分析 中華電信、遠傳、威寶上網速度折線圖2011-11~2013-02	55
圖37  遠傳2012-01~2012-10正面評價雷達圖	58
圖38  遠傳2012-01~2012-10負面評價雷達圖	58
圖39  遠傳2012-11~2013-02正面評價雷達圖	59
圖40  遠傳2012-01~2012-11負面評價雷達圖	60
圖41  五大電信於服務品質面向正評價及負評價的評價人數	62
圖42  遠傳2011-11~2013-02正面評價雷達圖	64
圖43  遠傳2011-11~2013-02負面評價雷達圖	64
圖44  五大電信在價格面向的評價折線圖	66
圖45  中華電信2012-10全民共省專案	67
圖46  中華電信2011-11~2012-09正面評價雷達圖	70
圖47  中華電信2011-11~2012-09負面評價雷達圖	70
圖48  中華電信全民共省2012-10正面評價雷達圖	71
圖49  中華電信全民共省2012-10正面評價雷達圖	72
圖50  三星手寫門討論流量示意圖(資料來源：OpView研究團隊)	80
圖51  收訊評價異常分析2012-01	80
圖52  收訊評價異常分析2012-02	81
圖53  收訊評價異常分析2012-03	81
圖54  收訊評價異常分析2012-04	82
圖55  收訊評價異常分析2012-05	82
圖56  收訊評價異常分析2012-06	83

表目錄
表1   意見元素	6
表2   電信2011-11~2012-06資料數量	35
表3   電信2012-07~2013-02資料數量	36
表4   系統輸出示意圖	36
表5   電信2012-11~2012-06準確率、回收率、F1值	37
表6   電信2012-07~2013-02準確率、回收率、F1值	37
表7   電信2011-11~2013-02準確率、回收率、F1平均	40
表8   電信四大面向的描述說明	43
表9   五大電信業者的討論文章總數	44
表10  中華電信在學生專案於2012年10月的部份正面評價文章段落	46
表11  威寶在收訊品質2011年11月的部份負面評價文章段落	51
表12  遠傳在上網速度面向於2012年3月的部份負面評價文章段落	56
表13  遠傳在上網訴度面向於2013年2月的部份正面評價文章段落	57
表14  五大電信服務品質績分表	62
表15  遠傳在服務品質面向於2012~2013年的部份負面評價文章段落	63
表16  中華電信2012-10全民共省專案正面評價文章段落	69
表17  ID 註冊中請稍後 亞太價格正面評價文章段落	74
表18  ID lili1129 亞太價格正面評價文章段落	76
表19  ID Arena Speedo對台灣大哥大正面評價於異常評價分析-1	84
表20  ID Arena Speedo對台灣大哥大正面評價於異常評價分析-2	85

[1]	簡立, "意見探勘系統設計," 淡江大學資訊工程研究所碩士論文, 2012.
[2]	陳子龍, "中文意見探勘系統之句法分析," 淡江大學資訊工程學系資訊網路與通訊研究所碩士論文, 2012.
[3]	N. Kobayashi, K. Inui, and Y. Matsumoto, "Opinion Mining from Web Documents: Extraction and Structurization," Information and Media Technologies, vol. 2, pp. 326-337, 2007.
[4]	S.-M. Kim and E. Hovy, "Determining the sentiment of opinions," presented at the Proceedings of the 20th international conference on Computational Linguistics, Geneva, Switzerland, 2004.
[5]	B. Liu and L. Zhang, "A Survey of Opinion Mining and Sentiment Analysis
Mining Text Data," C. C. Aggarwal and C. Zhai, Eds., ed: Springer US, 2012, pp. 415-463.
[6]	K. Dave, S. Lawrence, and D. M. Pennock, "Mining the peanut gallery: opinion extraction and semantic classification of product reviews," presented at the Proceedings of the 12th international conference on World Wide Web, Budapest, Hungary, 2003.
[7]	M. Gamon, A. Aue, S. Corston-Oliver, and E. Ringger, "Pulse: Mining Customer Opinions from Free Text
Advances in Intelligent Data Analysis VI." vol. 3646, A. Famili, J. Kok, J. Pena, A. Siebes, and A. Feelders, Eds., ed: Springer Berlin / Heidelberg, 2005, pp. 741-741.
[8]	T. Wilson, P. Hoffmann, S. Somasundaran, J. Kessler, J. Wiebe, Y. Choi, et al., "OpinionFinder: a system for subjectivity analysis," presented at the Proceedings of HLT/EMNLP on Interactive Demonstrations, Vancouver, British Columbia, Canada, 2005.
[9]	J. Huang, O. Etzioni, L. Zettlemoyer, K. Clark, and C. Lee, "RevMiner: an extractive interface for navigating reviews on a smartphone," presented at the Proceedings of the 25th annual ACM symposium on User interface software and technology, Cambridge, Massachusetts, USA, 2012.
[10]	B. Liu, M. Hu, and J. Cheng, "Opinion observer: analyzing and comparing opinions on the Web," presented at the Proceedings of the 14th international conference on World Wide Web, Chiba, Japan, 2005.
[11]	J. Yi and W. Niblack, "Sentiment mining in WebFountain," in Data Engineering, 2005. ICDE 2005. Proceedings. 21st International Conference on, 2005, pp. 1073-1083.
[12]	L.-W. Ku, H.-W. Ho, and H.-H. Chen, "Opinion mining and relationship discovery using CopeOpi opinion analysis system," Journal of the American Society for Information Science and Technology, vol. 60, pp. 1486-1503, 2009.
[13]	L. Chien-Liang, H. Wen-Hoar, L. Chia-Hoang, L. Gen-Chi, and E. Jou, "Movie Rating and Review Summarization in Mobile Environment," Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, vol. 42, pp. 397-407, 2012.
[14]	J. Arndt, "Role of product-related conversations in the diffusion of a new product," Journal of marketing Research, pp. 291-295, 1967.
[15]	A. M. Susskind, "I told you so! Restaurant customers' word-of-mouth communication patterns," The Cornell Hotel and Restaurant Administration Quarterly, vol. 43, pp. 75-85, 2002.
[16]	R. A. Westbrook, "Product/consumption-based affective responses and postpurchase processes," Journal of marketing research, pp. 258-270, 1987.
[17]	L. J. Harrison-Walker, "The measurement of word-of-mouth communication and an investigation of service quality and customer commitment as potential antecedents," Journal of Service Research, vol. 4, pp. 60-75, 2001.
[18]	T. Hennig-Thurau, G. Walsh, and G. Walsh, "Electronic word-of-mouth: motives for and consequences of reading customer articulations on the internet," International Journal of Electronic Commerce, vol. 8, pp. 51-74, 2003.
[19]	J. L. Heskett, W. E. Sasser, and L. A. Schlesinger, Service profit chain: SimonandSchuster. com, 1997.
[20]	E. Katz and P. F. Lazarsfeld, Personal Influence, The part played by people in the flow of mass communications: Transaction Publishers, 1970.
[21]	C. Gronroos, Service management and marketing: managing the moments of truth in service competition vol. 286: Lexington Books Lexington, MA, 1990.
[22]	E. W. Anderson and M. W. Sullivan, "The antecedents and consequences of customer satisfaction for firms," Marketing science, vol. 12, pp. 125-143, 1993.
[23]	E. J. McCarthy, S. J. Shapiro, and W. D. Perreault, Basic marketing: Richard D. Irwin, 1993.