社群網站與通訊軟體改變了人們溝通與聯繫的方式，也因此產生了大量值得分析的非結構化文字資料，但如何正確判斷語句及文章背後所乘載的意涵，以及如何進行非結構化文章分析成為大數據分析與知識管理中核心的分析議題。而中文的語句分析較為困難，尤其是如何正確斷詞及進行情感分析一直是正確判斷語句表達意涵的關鍵問題。
　　雖然已有大量研究分析文字與情感表達間的關係，而針對文字進行的情感分析已經廣泛的被應用推薦系統、聊天機器人、客服機器人及智慧型資訊系統等許多領域中。其中情感分析主要依賴不同語境所發展出各種的情感詞庫，加上中文具有簡體、繁體字體、習慣用語、地區方言用語、文化的差異用語等問題，使得情感分析更為困難。
本論文將以結合不同之中文語境之情感詞庫來進行中文文章情感分析，並應用批踢踢實業坊當中含有情緒成分的文章以及新浪微博之文章來進行情感分析，藉此來了解透過不同語境之結合對於改善文章情感分析之成效。

　　After years of research, the text has proved to have a close relationship with emotional expression, and sentiment analysis for writing has been widely used in many applications.
　　Different emotional vocabularies have been developed in different situations. In terms of Chinese characters, it is divided into Simplified Chinese and Traditional Chinese. This paper will use the emotional lexicon of different Chinese contexts to analyze the sentiment of Chinese articles. This paper will use the articles in the PTT that contain emotional components and Sina Weibo articles to conduct sentiment analysis. This process can understand that the combination of different contexts can improve the effectiveness of the sentiment analysis or not.

致謝 i
摘要 ii
Abstract iii
目錄 iv
圖目錄 vi
表目錄 vii
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 5
1.3 研究目的 7
1.4 研究架構 8
1.5 研究限制 8
第二章 文獻探討 9
2.1 情感和語言 9
2.2 情感分析 10
2.3 情感辭典 10
2.2.1 中文情感極性辭典 11
2.2.2 情感分析用詞語集 11
2.2.3 中文情感詞彙本體 12
2.4 CKIP 13
2.5 ICTCLAS 13
2.6 NLPIR 14
2.7 Jieba 15
2.8 SVM 15
第三章 研究方法 17
3.1中文情感辭典 17
3.2情緒分類 20
3.3資料擷取 21
3.4 Crawler 22
3.5分類計分方式 21
3.6實驗流程 23
第四章 實驗結果 25
實驗一：使用中文情感詞彙本體來進行情感標記 25
實驗二：使用結合過後的中文情感辭典來進行情感標記 27
擴充與校正 29
實驗三：使用結合並校正後的中文情感辭典來進行情感標記 30
實驗四：使用七種情緒分類的中文情感辭典來進行情感標記 32
第五章 結論 33
第六章 未來研究建議 35
參考文獻 36
附錄 39

[1] J. Li, Y. Xu, H. Xiong, Y. Wang, “Chinese text emotion classification based on emotion dictionary,” 2010 IEEE 2nd Symposium on Web Society, pp. 170-174, 2010
[2] F. Barbieri and H. Saggion, “Modelling irony in twitter: Feature analysis and evaluation,” In Proceedings of the 9th International Language Resources and Evaluation Conference , pp. 4258–4264, 2014
[3] J. M. Wilce, “Language and Emotion,” Cambridge University Press, 2009.
[4] 彭昱傑，聊天機器人系統設計與實作，國立中正大學碩士論文，民國106年
[5] A. Ortony and T. J. Turner, “What's Basic About Basic Emotions?” Psychological Review, Vol. 97, No. 3, pp.315-331,1990
[6] A. Foolen, “The relevance of emotion for language and linguistics,” January 2012
[7] B. Pang and L. Lee, “Opinion mining and sentiment analysis,” Foundations and Trends in Information Retrieval, vol. 2, no. 1-2, pp.1–135, 2008
[8] C. Whitelaw, N. Garg and S. Argamon, “Using appraisal groups for sentiment analysis,” In Proceedings of the 14th ACM international conference on Information and knowledge management, pp. 625-631, October 2005
[9] X. Wan, “Using bilingual knowledge and ensemble techniques for unsupervised Chinese sentiment analysis,” In Proceedings of the conference on empirical methods in natural language processing, pp. 553-561, 2008
[10] L. Zheng, H. Wang and S. Gao, “Sentimental feature selection for sentiment analysis of Chinese online reviews,” International journal of machine learning and cybernetics, vol. 9, no. 1, pp. 75-84, 2018
[11] F. Baider and G. Cislaru, “Linguistic Approaches to Emotions in Context,” John Benjamins Publishing Company, 2014
[12] T. Wilson, J. Wiebe and P. Hoffmann, “Recognizing contextual polarity in phrase-level sentiment analysis,” In Proceedings of the conference on human language technology and empirical methods in natural language processing, pp. 347-354, October 2005
[13] H. Peng, Y. Ma, Y. Li and E. Cambria, “Learning Multi-grained Aspect Target Sequence for Chinese Sentiment Analysis,” Knowledge-Based Systems, vol. 148, pp. 167–176, 2018
[14] L.W. Ku and H.H. Chen, “Mining Opinions from the Web: Beyond Relevance Retrieval,” Mining Web Resources for Enhancing Information Retrieval, vol. 58, no.12, pp. 1838-1850, August 2007
[15] P. Y. Lu, “Affective Lexicon in Chinese - Construction and Annotation,” 2015
[16] 簡之文，部落格文章情感分析之研究，淡江大學碩士論文，民國101年
[17] 陳建美，中文情感詞彙本體的構建及其應用，中國大連理工大學博士論文，民國98年
[18] 王中楚，情緒與料庫建構技術之研究─以財經新聞為例，東吳大學商學院碩士論文，民國102年
[19] 楊邵為，Facebook 文章情緒分類器之設計與實作，國立中正大學碩士論文，民國106年
[20] 張日威，應用LDA進行Plurk主題分類及使用者情緒分析，國立雲林科技大學碩士論文，民國103年
[21] T. Joachims, “Text categorization with support vector machines: learning with many relevant features,” ECML'98 Proceedings of the 10th European Conference on Machine Learning, Pages 137-142,1998
[22] T. Masuyama and H. Nakagawa, “Applying cascaded feature selection to SVM text categorization,” 13th International Workshop on Database and Expert Systems Applications, pp.241–245, 2002
[23] H. Yu, J. Han and K. C. C. Chang, “PEBL: positive example based learning for web page classification using SVM,” In Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 239-248, July 2002