由於電子商城蓬勃發展，人們的消費習慣也隨著改變。在過去，人們在購買商品前，通常是先透過親友之間的口耳相傳的方式得知該商品的產品評價後，再進行消費；而在現今消費者在購買商品前，通常會透過網路上的討論區或論壇，取得他人對於該商品有關的意見評論，在進行消費，為了能有效且快速取得文章內有關產品或是商家資訊，因此中文意見探勘系統就為之重要。本論文主要是修正(陳子龍 2012)所提出的句型文法，歸納出四種可以修正的錯誤並且加以修正，其中三種是不符合文法規則的錯誤，分別是對等句中的連接句錯誤、比較句中的不符合文法規則錯誤以及一般句的Topic繼承錯誤，而剩下的一種是一般句中的意見矛盾的問題。實驗結果顯示各月份和不同討論區之準確率、回收率和F1均有提升，雖然提升不多，但是從實驗結果之中，顯示我們所修正的方法是正確以及有成效的。

With the maturation of the e-commerce, people's consumption habit has changed. In the past, before consumer purchased product, they know the product’s evaluation from their friends or relatives. Today, they can know the product’s evaluation form other people's comments on the website such as Internet forums and discussion groups. In order to obtain the Chinese articles about products or manufacturer’s information correctly and effectively, the Chinese opinion mining system is important.
In our study, we improved the sentence analysis grammar defects of the Chinese opinion mining system [1] which are : (1) Coordination sentence error problem(2) Comparative sentences does not comply with the rules of grammar errors (3) The general sentence topic inherited error (4) The contradictions error of the general sentence.We proposed the statistical algorithm to improve the contradictions error. The experimental results shows the method can enhance the precison and recall.

目錄
第1章 緒論	1 
1.1 研究動機與目的	1
1.2 研究架構	3
第2章 文獻探討	5
2.1 意見單元定義	5
2.2 意見極性判斷	8
2.3 意見元素搭配	9
第3章 句型文法	13
3.1 陳子龍 ’ s work	13
3.1.1 預設Topic	13
3.1.2 意見元素類別轉換	17
3.1.3 意見元素配對方法	18
3.1.4 句型配對以及意見傾向判斷	22
3.2 數據探討	30
3.2.1 準確率錯誤分析	32
3.2.2 回收率遺失分析	38
3.3 文法修正以及統計修正	42
第4章 文法及極性的修正	43
4.1 對等句修正	43
4.2 比較句修正	44
4.3 一般句修正	45
4.3.1 Topic繼承錯誤修正	45
4.3.2 意見矛盾的修正	46
第5章 實驗討論	54
5.1 電信實驗結果	55
5.2 網路實驗結果	59
第6章 結論以及未來研究	62
參考文獻	64
附錄-英文論文	67

圖目錄
圖 1句子經過Parser分析後	10
圖 2 CKIP Pattern	11
圖 3短篇文章預設Topic之範例	15
圖 4長篇文章預設Topic之範例	16
圖 5意見元素轉換Feature之範例	17
圖 6意見元素無轉換Feature之範例	18
圖 7一般句配對之範例	22
圖 8轉折句配對之範例	24

表目錄
表格 1意見元素	6
表格 2特徵詞Pattern	9
表格 3 Feature和Opinion Word(OP)對應表	20
表格 4 Topic與產品之間的對應表	20
表格 5轉折詞表	24
表格 6連接詞表	25
表格 7否定詞表	28
表格 8疑問詞表	29
表格 9假設詞表	29
表格 10系統輸出示意圖	30
表格 11 Mobile01電信各月整體數據	31
表格 12 Mobile01網路各月整體數據	31
表格 13 PTT電信各月整體數據	31
表格 14 PTT網路各月整體數據	31
表格 15 Mobile01電信各月影響準確率原因筆數	32
表格 16 Mobile01網路各月影響準確率原因筆數	32
表格 17 PTT電信各月影響準確率原因筆數	33
表格 18 PTT網路各月影響準確率原因筆數	33
表格 19 Mobile01電信各月影響回收率原因筆數	38
表格 20 Mobile01網路影響回收率原因筆數	38
表格 21 PTT電信各月影響回收率原因筆數	38
表格 22 PTT網路各月影響回收率原因筆數	39
表格 23錯誤可修正表	42
表格 24 Mobile01電信資料量	54
表格 25 Mobile01網路資料量	54
表格 26 Mobile01修正前電信各月整體數據	55
表格 27 Mobile01修正後電信各月整體數據	55
表格 28經比較句以及連接句修正後多的錯誤筆數	56
表格 29電信準確率未修正部分	57
表格 30 Mobile01電信各月影響回收率原因筆數比較	57
表格 31電信回收率未修正部分	58
表格 32 Mobile01修正前網路各月整體數據	59
表格 33 Mobile01修正後網路各月整體數據	59
表格 34網路比較修正句數表	60
表格 35網路準確率未修正部分	60
表格 36回收率修正比較	61
表格 37網路回收率未修正部分	61
表格 38沒敘述句時準確率	62

Bin, S. and C. Kuiyu (2006). Mining Chinese Reviews. Data Mining Workshops, 2006. ICDM Workshops 2006. Sixth IEEE International Conference on.
	
Chan, K. T. (2009). Improving Opinion Mining with Feature-opinion Association and Human Computation, Chinese University of Hong Kong.
	
Chen, M. and T. Yao (2010). Combining dependency parsing with shallow semantic analysis for Chinese opinion-element relation identification. Universal Communication Symposium (IUCS), 2010 4th International.
	
Chien-Liang, L., H. Wen-Hoar, et al. (2012). "Movie Rating and Review Summarization in Mobile Environment." Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on 42(3): 397-407.
	
Ding, X., B. Liu, et al. (2008). A holistic lexicon-based approach to opinion mining, ACM.
	
Hatzivassiloglou, V. and K. R. McKeown (1997). Predicting the semantic orientation of adjectives, Association for Computational Linguistics.
	
Hu, M. and B. Liu (2004). Mining and summarizing customer reviews. Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining. Seattle, WA, USA, ACM: 168-177.
	
Kim, S.-M. and E. Hovy (2004). Determining the sentiment of opinions. Proceedings of the 20th international conference on Computational Linguistics. Geneva, Switzerland, Association for Computational Linguistics: 1367.
	
Kobayashi, N., K. Inui, et al. (2007). "Opinion Mining from Web Documents: Extraction and Structurization." Information and Media Technologies 2(1): 326-337.
	
Ku, L.-W. and H.-H. Chen (2007). "Mining opinions from the Web: Beyond relevance retrieval." Journal of the American Society for Information Science and Technology 58(12): 1838-1850.
	
Ku, L. W., I. C. Liu, et al. (2008). "Sentence-Level Opinion Analysis by CopeOpi in NTCIR-7."
	
Li, Z., M. Zhang, et al. (2009). Automatic Extraction for Product Feature Words from Comments on the Web
Information Retrieval Technology. G. Lee, D. Song, C.-Y. Linet al, Springer Berlin / Heidelberg. 5839: 112-123.
	
Liu, B. and L. Zhang (2012). A Survey of Opinion Mining and Sentiment Analysis
Mining Text Data. C. C. Aggarwal and C. Zhai, Springer US: 415-463.
	
Mukherjee, S. and P. Bhattacharyya (2012). Feature Specific Sentiment Analysis for Product Reviews. Computational Linguistics and Intelligent Text Processing. A. Gelbukh, Springer Berlin Heidelberg. 7181: 475-487.
	
Qadir, A. (2009). Detecting opinion sentences specific to product features in customer reviews using typed dependency relations. Proceedings of the Workshop on Events in Emerging Text Types. Borovets, Bulgaria, Association for Computational Linguistics: 38-43.
	
Qiang, Y., S. Wen, et al. (2006). Sentiment Classification for Movie Reviews in Chinese by Improved Semantic Oriented Approach. System Sciences, 2006. HICSS '06. Proceedings of the 39th Annual Hawaii International Conference on.
	
Qiu, G., B. Liu, et al. (2009). Expanding domain sentiment lexicon through double propagation, Morgan Kaufmann Publishers Inc.
	
Qiu, G., B. Liu, et al. (2011). "Opinion Word Expansion and Target Extraction through Double Propagation." Computational Linguistics 37(1): 9-27.
	
Ting-Chun, P. and S. Chia-Chun (2010). An Unsupervised Snippet-Based Sentiment Classification Method for Chinese Unknown Phrases without Using Reference Word Pairs. Web Intelligence and Intelligent Agent Technology (WI-IAT), 2010 IEEE/WIC/ACM International Conference on.
	
Ting-Chun, P. and S. Chia-Chun (2010). Using Chinese part-of-speech patterns for sentiment phrase identification and opinion extraction in user generated reviews. Digital Information Management (ICDIM), 2010 Fifth International Conference on.
	
Titov, I. and R. McDonald (2008). "A joint model of text and aspect ratings for sentiment summarization." Urbana 51: 61801.
	
Turney, P. D. (2002). Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews. Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. Philadelphia, Pennsylvania, Association for Computational Linguistics: 417-424.
	
Wang, B. and H. Wang (2007). Bootstrapping both product properties and opinion words from Chinese reviews with cross-training. Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence, IEEE Computer Society.
	
Wu, L., Y. Zhou, et al. (2011). Generating Syntactic Tree Templates for Feature-Based Opinion Mining. Advanced Data Mining and Applications. J. Tang, I. King, L. Chen and J. Wang, Springer Berlin Heidelberg. 7121: 1-12.
	
Xu, G., C.-R. Huang, et al. (2013). Extracting Chinese Product Features: Representing a Sequence by a Set of Skip-Bigrams. Chinese Lexical Semantics. D. Ji and G. Xiao, Springer Berlin Heidelberg. 7717: 72-83.
	
Zhai, Z., B. Liu, et al. (2011). Identifying evaluative sentences in online discussions.
	
Zhang, C., D. Zeng, et al. (2009). "Sentiment analysis of Chinese documents: From sentence to document level." J. Am. Soc. Inf. Sci. Technol. 60(12): 2474-2487.
	
Zhang, S., W. Jia, et al. (2010). "Extracting Product Features and Sentiments from Chinese Customer Reviews."
	
Zhuang, L., F. Jing, et al. (2006). Movie review mining and summarization, ACM.
	
李林琳 (2008). 基于特定领域的汉语句子意见挖掘, 上海交通大学.
	
陳子龍 (2012). "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.
	
瞿怡正 (2012). "Mobile01和PTT兩個不同論壇相同面向習慣用語之探討-以電信寬頻為例." 淡江大學資訊工程研究所碩士論文.