臺灣博碩士論文加值系統

近年來，找出音樂的特徵及建立音樂與情緒間的關聯性，並判斷音樂所表達的情緒成了很重要的議題。本論文致力於收集歌詞的情緒標籤並且建立分類模型來偵測歌詞中的情緒。為了收集歌詞的情緒標籤，我們製作了兩個人類計算( Human Computation) 的遊戲並結合了Facebook的社群功能。在第一個遊戲中，我們讓玩家回答一些標記問題，並且在玩家作答時收集情緒標籤。在第二個遊戲中，我們透過收集複數個標籤來驗證標籤的正確性。在收集完標籤後，我們利用歌詞中語意及文法的特徵並使用半監督式學習來訓練分類模型。相較於音樂訊號，歌詞較缺乏旋律的資訊，因此我們也提出一些新的特徵來從歌詞中取得節奏的資訊。

This thesis aims at collecting lyrics sentiment labels for creating a classification model to detect the emotion of songs. To collect the labels of the lyrics, we propose two human computation games. In the first game, the emotion labels are collected when players answer some annotation questions about Chinese lyric. In the second game, multiple labels of a song are collected for verification purpose. The games are implemented with Facebook API. The second goal of this thesis is to construct a model for lyric sentiment detection. We propose several syntactic and semantic features and exploit the semi-supervised learning approaches to learn the classification model. Furthermore, some heuristics are proposed to extract information about the tempo of songs from text to compensate for the insufficient melodic information in lyrics.

中文摘要 i
ABSTRACT ii
CONTENTS iii
LIST OF FIGURES v
LIST OF TABLES vi
Chapter 1 Introduction 1
Chapter 2 Related Work 4
2.1 Emotion model 4
2.2 Human computation application 5
2.3 Lyrics approach for emotion classification 7
Chapter 3 Human computation games: LyricsMatcher and Song-request 9
3.1 Game Mechanisms: LyricsMatcher 9
3.2 Game Mechanisms: Song-request 12
3.3 Song preprocessing and partition 13
Chapter 4 Lyrics emotion classification 15
4.1 lyrics features 15
4.2 semi-supervised learning 17
Chapter 5 Experiment 18
5.1 lyrics features 18
5.2 semi-supervised learning and heuristic features 19
Chapter 6 Conclusion 21
REFERENCE 22

[1]Von Ahn, L. (2006). Games with a purpose. Computer, 39(6): 92-94.
[2]Von Ahn, L., Maurer, B., McMillen, C., Abraham, D., & Blum, M. (2008). reCAPTCHA: Human-based character recognition via web security measures. Science, 321(5895): 1465-1468.
[3]Von Ahn, L., & Dabbish, L. (2004, April). Labeling images with a computer game. In Proceedings of the SIGCHI conference on Human factors in computing systems (pp. 319-326). ACM.
[4]Von Ahn, L., Liu, R., & Blum, M. (2006, April). Peekaboom: a game for locating objects in images. In Proceedings of the SIGCHI conference on Human Factors in computing systems (pp. 55-64). ACM.
[5]Hu, X., & Downie, J. S. (2007, September). Exploring Mood Metadata: Relationships with Genre, Artist and Usage Metadata. In ISMIR (pp. 67-72).
[6]Russell, J. A. (1980). A circumplex model of affect. Journal of personality and social psychology, 39(6): 1161.
[7]Ho, C. J., Chang, T. H., Lee, J. C., Hsu, J. Y. J., & Chen, K. T. (2009, June). KissKissBan: a competitive human computation game for image annotation. In Proceedings of the acm sigkdd workshop on human computation (pp. 11-14). ACM.
[8]Mandel, M. I., & Ellis, D. P. (2008). A web-based game for col-lecting music metadata. Journal of New Music Research, 37(2): 151-165.
[9]Turnbull, D., Liu, R., Barrington, L., & Lanckriet, G. R. (2007, September). A Game-Based Approach for Collecting Semantic Annotations of Music. In ISMIR (Vol. 7, pp. 535-538).
[10]Law, E. L., Von Ahn, L., Dannenberg, R. B., & Crawford, M. (2007, September). TagATune: A Game for Music and Sound Annotation. In ISMIR (Vol. 3, p. 2).
[11]Kim, Y. E., Schmidt, E. M., & Emelle, L. 2008, February. MoodSwings: A Collaborative Game for Music Mood Label Collection. In ISMIR (Vol. 8, pp. 231-236).
[12]Scharl, A., & Weichselbraun, A. (2008). An automated approach to investigating the online media coverage of US presidential elections. Journal of Information Technology & Politics, 5(1), 121-132.
[13]Aras, H., Krause, M., Haller, A., & Malaka, R. (2010, July). Webpardy: harvesting QA by HC. In Proceedings of the ACM SIGKDD Workshop on Human Computation (pp. 49-52). ACM.
[14]Yang, Y. H., Lin, Y. C., Cheng, H. T., Liao, I. B., Ho, Y. C., & Chen, H. H. (2008). Toward multi-modal music emotion classification. In Advances in Multimedia Information Processing-PCM 2008 (pp. 70-79). Springer Berlin Heidelberg.
[15]Mehrabian, A., & Russell, J. A. (1974). An approach to environmental psychology. the MIT Press.
[16]Bradley, M. M., & Lang, P. J. (1999). Affective norms for English words (ANEW): Instruction manual and affective ratings (pp. 1-45). Technical Report C-1, The Center for Research in Psychophysiology, University of Florida.
[17]Hu, Y., Chen, X., & Yang, D. (2009, August). Lyric-based Song Emotion Detection with Affective Lexicon and Fuzzy Clustering Method. In ISMIR (pp. 123-128).
[18]Hu, X., Downie, J. S., & Ehmann, A. F. (2009). Lyric text mining in music mood classification. American music, 183(5,049), 2-209.
[19]Van Zaanen, M., & Kanters, P. (2010, August). Automatic Mood Classification Using TF* IDF Based on Lyrics. In ISMIR (pp. 75-80).
[20]Lu, Q., Chen, X., Yang, D. & Wang, J. (2010). Boosting for Multi-Modal Music Emotion Classification.. In J. S. Downie & R. C. Veltkamp (eds.), ISMIR (p./pp. 105-110), : International Society for Music Information Retrieval. ISBN: 978-90-393-53813
[21]Ku, L. W., Liang, Y. T., & Chen, H. H. (2006, March). Opinion Extraction, Summarization and Tracking in News and Blog Corpora. In AAAI spring symposium: Computational approaches to analyzing weblogs (Vol. 100107).