臺灣博碩士論文加值系統

本研究為基於多種情緒辭典與常識網路以協助分析歌詞文本之情緒。此研究可應用於以情緒為主的推薦系統或搜尋引擎等相關研究。由於現今除了英語的情緒詞語資源較豐富外，其餘語言則常因為情緒詞語資源的不完善，不容易挖掘文本情緒或是作更進一步的應用。因此，提出一語言獨立的情緒詞語擴散方法來得到較完善的情緒詞語辭典是本研究的重點。

目前情緒分析的應用，往往只基於一種情緒辭典，我們為了增加的情緒詞語資料的完整性，收集了九種不同類型的情緒辭典，並利用辭典間相互驗證的方法來增加情緒詞語資料的正確性。

透過常識網路(ConceptNet)具有大量知識且概念與概念間互相連接的特性，藉由情緒擴散激發，將情緒詞語種子的情緒值擴散到相鄰的概念，傳遞到整個常識網路，得到擴散後的情緒辭典，我們稱之為iSentiDictionary。其包含28,248個詞語(9,701個單字與18,547的概念)，且每個詞語皆分配一個情緒分數，介於-1和1之間。

之後，我們利用所建構的iSentiDictionary預測歌詞文本情緒值，其情緒誤差距離為0.4568，比起利用翻譯ANEW情緒辭典的誤差距離0.7315，降低了0.2747。

This thesis presents a new approach to language independent sentiment analysis that combines multi-dictionary and commonsense knowledgebase.

Sentiment analysis is the task of identifying positive and negative opinions, emotions, and evaluations. One major impediment to Non-English sentiment analysis research is the lack of a complete sentiment dictionary. In light of this, we collected nine kinds of sentiment dictionaries as sentiment concept seed, then through sentiment spreading activation from common sense network (ConceptNet) to get more sentiment concepts. And got a sentiment dictionary named iSentiDictionary. iSentiDictionary contains 28,248 sentiment terms (9,701 words and 18,547 concepts), and assigned a sentiment score between -1 and 1 for each sentiment term.

Final, we used iSentiDictionary to mine sentiment from Chinese pop song dataset (iPop).Compared to use the translation of ANEW as sentiment dictionary, iSentiDictionary reduced the error distance from 0.7315 to 0.4568.

Acknowledgments i
Abstract ii
List of Figures vii
List of Tables viii
Chapter 1 緒論1
1.1 研究動機. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 問題定義. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.3 研究方法與架構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.3.1 情緒擴散模組. . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.3.2 情緒挖掘模組. . . . . . . . . . . . . . . . . . . . . . . . . . . 4
1.4 論文結構. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
Chapter 2 情緒辭典介紹6
2.1 標記情緒值辭典. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.1.1 Affective Norms for English Words . . . . . . . . . . . . . . . 7
2.1.2 SenticNet . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
2.1.3 SentiWordNet . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.2 標記情緒極性辭典. . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
2.2.1 知網-情感分析用詞語集. . . . . . . . . . . . . . . . . . . . . 10
2.2.2 General Inquirer-Emotion . . . . . . . . . . . . . . . . . . . . 12
2.2.3 WordNet-Affect . . . . . . . . . . . . . . . . . . . . . . . . . . 13
2.2.4 National Taiwan University Sentiment Dictionary . . . . . . . 14
2.3 標記情緒詞語辭典. . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
2.3.1 Never Ending Language Learner-Emotion . . . . . . . . . . . 15
2.3.2 WeFeelFine . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
2.4 情緒辭典特性觀察. . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
2.4.1 標記方法. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
2.4.2 標記內容. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
2.4.3 標記類型. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
Chapter 3 情緒擴散模組20
3.1 情緒單元種子收集. . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
3.1.1 翻譯情緒辭典. . . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.1.2 情緒辭典擴張. . . . . . . . . . . . . . . . . . . . . . . . . . . 24
3.1.3 情緒辭典合併. . . . . . . . . . . . . . . . . . . . . . . . . . . 26
3.2 情緒擴散激發. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
3.2.1 常識網路(Common Sense Network) . . . . . . . . . . . . . . . 28
3.2.2 基本的擴散激發. . . . . . . . . . . . . . . . . . . . . . . . . . 29
3.2.3 自我學習的擴散激發. . . . . . . . . . . . . . . . . . . . . . . 31
Chapter 4 情緒分析模組35
4.1 自然語言處理. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
4.1.1 Yahoo! 斷章取義. . . . . . . . . . . . . . . . . . . . . . . . . 37
4.2 句子情緒挖掘. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
4.2.1 情緒單元挖掘. . . . . . . . . . . . . . . . . . . . . . . . . . . 39
4.2.2 程度詞處理. . . . . . . . . . . . . . . . . . . . . . . . . . . . 39
4.2.3 否定詞處理. . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
4.2.4 轉折詞處理. . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
4.3 文本情緒挖掘. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
Chapter 5 實驗設計與結果43
5.1 情緒擴散模組實驗設計與結果. . . . . . . . . . . . . . . . . . . . . . 43
5.2 情緒分析模組實驗設計與結果. . . . . . . . . . . . . . . . . . . . . . 47
Chapter 6 結論與未來展望51
6.1 貢獻. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52
6.2 未來展望. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52
Bibliography 53

[1] S. Baccianella, A. Esuli, and F. Sebastiani. Sentiwordnet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. In Seventh conference on International Language Resources and Evaluation, Malta. Retrieved May, volume 25, page 2010, 2010.
[2] L. Balkwill and W. F. Thompson. A cross-cultural investigation of the perception of emotion in music: Psychophysical and cultural cues: Psychophysical and culturalcues. Music Perception, 17(1):43–46, 1999.
[3] M. Bradley and P. Lang. Affective norms for english words (anew): Instruction manual and affective ratings. University of Florida: The Center for Research in Psychophysiology, 1999.
[4] E. Cambria, A. Hussain, C. Havasi, and C. Eckl. Affectivespace: Blending common sense and affective knowledge to perform emotive reasoning. WOMSA at CAEPIA, Seville, 2009.
[5] E. Cambria, A. Hussain, C. Havasi, and C. Eckl. Sentic computing: Exploitation of common sense for the development of emotion-sensitive systems. Development of Multimodal Interfaces: Active Listening and Synchrony, pages 148–156, 2010.
[6] E. Cambria, R. Speer, C. Havasi, and A. Hussain. Senticnet: A publicly available semantic resource for opinion mining. In 2010 AAAI Fall Symposium Series, 2010.
[7] A. Carlson, J. Betteridge, B. Kisiel, B. Settles, E. Hruschka Jr, and T. Mitchell. Toward an architecture for never-ending language learning. In Proceedings of the Twenty-Fourth Conference on Arti cial Intelligence (AAAI 2010), volume 2, pages 3–3, 2010.
[8] A. Chen, Y. Zhou, A. Zhang, and G. Sun. Unigram language model for chinese word segmentation. In Proceedings of the 4th SIGHAN Workshop on Chinese Language Processing, pages 138–141, 2005.
[9] P. Dodds and C. Danforth. Measuring the happiness of large-scale written expression: Songs, blogs, and presidents. Journal of Happiness Studies, 11:441–456, 2010.
[10] A. Esuli and F. Sebastiani. Sentiwordnet: A publicly available lexical resource for opinion mining. In Proceedings of LREC, volume 6, pages 417–422. Citeseer, 2006.
[11] C. Havasi, R. Speer, and J. Alonso. Conceptnet 3: a flexible, multilingual semantic network for common sense knowledge. In Recent Advances in Natural Language Processing. Citeseer, 2007.
[12] D. C. Hsu. iPlayr: an emotion-aware music player. Master’s thesis, National Taiwan University, 2007.
[13] Y. Hu, X. Chen, and D. Yang. Lyric-based song emotion detection with affective lexicon and fuzzy clustering method. In Proceedings of the 10th International Conference on Music Information Retrieval (ISMIR''09), 2009.
[14] S. Kamvar and J. Harris. We feel fine and searching the emotional web. In Proceedings of the fourth ACM international conference on Web search and data mining, pages 117–126. ACM, 2011.
[15] L. Ku, Y. Liang, and H. Chen. Opinion extraction, summarization and tracking in news and blog corpora. In Proceedings of AAAI-2006 Spring Symposium on Computational Approaches to Analyzing Weblogs, 2006. knowledge. In Proceedings of the 8th international conference on Intelligent user interfaces, pages 125–132. ACM, 2003.
[18] J. Mei, Y. Zhu, Y. Gao, and H. Yin. tong2yi4ci2ci2lin2, 1982.
[19] P. Singh. The public acquisition of commonsense knowledge. In Proceedings of AAAI Spring Symposium: Acquiring (and Using) Linguistic (and World) Knowledge for Information Access, 2002.
[20] P. Stone, D. Dunphy, and M. Smith. The general inquirer: A computer approach to content analysis. 1966.
[21] C. Strapparava and A. Valitutti. Wordnet-affect: an affective extension of wordnet. In Proceedings of LREC, volume 4, pages 1083–1086. Citeseer, 2004.
[22] W.-j. Wang. An emotion recognition mechanism based on. mutual information and semantic clues. Master’s thesis, National University of Tainan Institutional Repository Master Program of Information and Learning Technology, 2009.
[23] Y.-S.Wu. Affective lyrics analysis for mood estimation of chinese pop music. Master’s thesis, National Taiwan University, 2009.
[24] Y. Xia, L. Wang, K. Wong, and M. Xu. Sentiment vector space model for lyric-based song sentiment classification. Proc. of the Association for Computational Linguistics. Columbus, Ohio, USA: ACL-08, pages 133–136, 2008.
[25] D. Yarowsky. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the 33rd annual meeting on Association for Computational Linguistics, pages 189–196. Association for Computational Linguistics, 1995.