近年來，隨著微網誌服務的興起，有越來越多的人透過在微網誌上發表文章來抒發情感，而表情符號是使用者最常用來傳達情感的方式。然而，目前欲在微網誌上標記表情符號仍有許多不便之處，因此，本論文擬研發一個根據使用者的發文內容做表情符號推薦之系統。在本論文中，微網誌文章被假設具有情緒波動(emotion fluctuation)的特性。我們首先將微網誌的文章以一個固定長度的滑動視窗將其切割成數個片段，並從這些片段中探勘出樣本(pattern)做為除了詞袋(bag-of-word)外的另一種特徵參數，然後這些片段的特徵向量再透過潛在狄式配置(latent Dirichlet allocation, 簡稱LDA)在表情符號空間上投影成表情符號剖面(emoticon profiles)，將每一篇微網誌的文章所產生之表情符號剖面序列表示成情感軌跡(affective trajectory)。由於不同的情緒可能有類似的情感軌跡， 我們採用k-中心點(k-medoids)聚類演算法及豪斯多夫距離(Hausdorff distance)為基礎的相似度量測於情感軌跡分類。各分類中每一表情符號的情感軌跡以對數線型(log-linear)模型表示，並與各類別模型作比較，以作為輸入之微網誌文章表情符號推薦之依據。為了驗證我們方法的效能，我們從噗浪(Plurk)上抓下微網誌語料進行訓練跟驗證，實驗結果顯示我們的效果較過去的方法有較佳的表現。

Recently, with the rise of microblogging service, people like to express their feelings through posting microblog articles. Together with the articles, emoticons are often used to express their affective states. However, current practice is inconvenient while choosing or tagging emoticons. This thesis proposed an emoticon recommendation system based on the content of the post. In this study, microblog posts are assumed to embed with fluctuating emotions. Fixed-sized sliding windows are applied to split the post into several segments for pattern feature mining. The feature vectors are further projected to an emoticon space based on an LDA-based model to form emoticon profile sequence as an affective trajectory. The k-medoids clustering algorithm with Hausdorff distance was applied to cluster the affective trajectories. The recommended emoticon for an input microblog was finally determined by a log-linear model. The proposed approach was verified using microblogs crawled from Plurk. The results show that our method outperforms the classical LDA approach.

[1] R. Cai, C. Zhang, C. Wang, L. Zhang, and W. Y. Ma, “Musicsense: contextual music recommendation using emotional allocation modeling,” In Proceedings of the 15th international conference on Multimedia, ACM, 2007, pp. 553-556.
[2] X. Wang, C. Zhang, Ji Y. Sun, L. Wu, and Z. Bao, “A Depression Detection Model Based on Sentiment Analysis in Micro-blog Social Network,” In Trends and Applications in Knowledge Discovery and Data Mining, Springer , 2013, pp. 201-213.
[3] L. Coviello , Y. Sohn , A. D. Kramer, C. Marlow , M. Franceschetti , N. A. Christakis, and J. H. Fowler “Detecting Emotional Contagion in Massive Social Networks,” PLoS One. Mar 2014.
[4] R. W. Picard, “Affective Computing,” MIT Press, Cambridge, 1997.
[5] P. Ekman, “An argument for basic emotions,” Cognition & Emotion, vol. 6, no. 3-4, pp. 169-200, 1992.
[6] J. A. Russell, “A circumplex model of affect,” Journal of Personality and Social Psychology, vol. 39, pp. 1161-1178, 1980.
[7] M. E. Ayadi, M. S. Kamel, and F. Karray, “Survey on speech emotion recognition: Features, classification schemes, and databases,” Pattern Recognition, vol. 44, no. 3, pp. 572–587, March 2011.
[8] B. Fasel, and J. Luettin, “Automatic facial expression analysis: a survey,” Pattern recognition, vol. 36, no. 1, pp. 259-275, 2003.
[9] R. B. Knapp, J. Kim and E. André, “Physiological signals and their use in augmenting emotion recognition for human–machine interaction,” In Emotion-Oriented Systems, Springer, 2011, pp. 133-159.
[10] C. H. Wu, and W. B. Liang, “Emotion recognition of affective speech based on multiple classifiers using acoustic-prosodic information and semantic labels,” IEEE Transactions on Affective Computing, vol. 2, no. 1, pp. 10-21, 2011.
[11] B. Liu, ”Sentiment analysis and opinion mining,” Synthesis Lectures on Human Language Technologies, vol. 5,no. 1, pp. 1-167, 2012.
[12] S. Morinaga, K. Yamanishi, K. Tateishi, and T. Fukushima, “Mining product reputations on the web,” In Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, July, ACM, 2002,pp. 341-349.
[13] M. Hu, and B. Liu, “Mining and summarizing customer reviews,” In Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, August 2004, pp. 168-177.
[14] A. M. Popescu, and O. Etzioni, “Extracting product features and opinions from reviews,” In Natural language processing and text mining, Springer, 2007, pp. 9-28.
[15] B. Pang, L. Lee, and S. Vaithyanathan, “Thumbs up?: sentiment classification using machine learning techniques,” In Proceedings of the ACL-02 conference on Empirical methods in natural language processing-Volume 10, ACL, July 2002, pp. 79-86.
[16] C. Ma, H. Prendinger, and M. Ishizuka, “Emotion estimation and reasoning based on affective textual interaction,” In Affective computing and intelligent interaction, Springer, 2005, pp. 622-628.
[17] J. T. Hancock, C. Landrigan, and C. Silver, “Expressing emotion in text-based communication,” In Proceedings of the SIGCHI conference on Human factors in computing systems, ACM, April 2007, pp. 929-932.
[18] C. Strapparava, and A. Valitutti, “WordNet Affect: an Affective Extension of WordNet,” In Proceedings of Language Resources and Evaluation Conference -Volume 4, May 2004, pp. 1083-1086.
[19] A. Esuli, and F. Sebastiani, “Sentiwordnet: A publicly available lexical resource for opinion mining,” In Proceedings of Language Resources and Evaluation Conference-Volume 6, May 2006, pp. 417-422.
[20] M. M. Bradley, and P. J. Lang, “Affective norms for English words (ANEW): Instruction manual and affective ratings,” In Technical Report C-1, The Center for Research in Psychophysiology, University of Florida, 1999, pp. 1-45.
[21] Y. R. Tausczik, and J. W. Pennebaker, “The psychological meaning of words: LIWC and computerized text analysis methods,” Journal of language and social psychology, vol. 29, no. 1, pp. 24-54, 2010.
[22] Z. Teng, F. Ren, and S. Kuroiwa “Retracted: recognition of emotion with SVMs,” In Computational Intelligence , Springer, 2006, pp. 701-710.
[23] C. Yang, K. H. Lin, and H. H. Chen, “Emotion classification using web blog corpora,” In IEEE/WIC/ACM International Conference on Web Intelligence, November 2007, pp. 275-278.
[24] A. Pak, and P. Paroubek “Twitter based system: Using Twitter for disambiguating sentiment ambiguous adjectives,” In Proceedings of the 5th International Workshop on Semantic Evaluation, ACL, July 2010, pp. 436-439.
[25] C. H. Wu, Z. J. Chuang, and Y. C. Lin, “Emotion recognition from text using semantic labels and separable mixture models,” ACM transactions on Asian language information processing (TALIP), vol. 5, no.2, pp. 165-183, 2006.
[26] S. Bao, S. Xu, L. Zhang, R. Yan, Z. Su, D. Han, and Y. Yu, “Mining social emotions from affective text,” IEEE Transactions on Knowledge and Data Engineering , vol. 24, no. 9, pp. 1658-1670, 2012.
[27] Y. Kim, and E. M. Provost, “Emotion classification via utterance-level dynamics: A pattern-based approach to characterizing affective expressions,” In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2013, pp. 3677-3681.
[28] S. C. Deerwester, S. T. Dumais, T. K. Landauer, G. W., Furnas, and R. A. Harshman, “Indexing by latent semantic analysis,” Journal of The American Society For Information Science, vol. 41, no. 6, pp. 391-407, 1990.
[29] T. Hofmann, “Unsupervised learning by probabilistic latent semantic analysis,” Machine learning, vol. 42, no. 1-2, pp. 177-196, 2001.
[30] D. M. Blei, A. Y. Ng, and M. I. Jordan, “Latent dirichlet allocation,” Journal of machine Learning research, vol. 3, pp. 993-1022, 2003.
[31] W. Y. Ma, and K. J. Chen, “A bottom-up merging algorithm for Chinese unknown word extraction,” In Proceedings of the second SIGHAN workshop on Chinese language processing-Volume 17, ACL, July 2003, pp. 31-38.
[32] C. Borgelt, “Efficient implementations of apriori and eclat,” In FIMI’03: Proceedings of the IEEE ICDM workshop on frequent itemset mining implementations, November 2003.
[33] A. P. Reynolds, G. Richards, B. de la Iglesia, and V. J. Rayward-Smith, “Clustering rules: a comparison of partitioning and hierarchical clustering algorithms,” Journal of Mathematical Modelling and Algorithms, vol. 5, no. 4, pp. 475-504, 2006.
[34] G. Ayala, M. C. López-Díaz, M. López-Díaz, and L. Martínez-Costa, “Methods and Algorithms to Test the Hausdorff and Simplex Dispersion Orders with an R Package,” In Methodology and Computing in Applied Probability, Springer, 2013, pp. 1-15.
[35] C. K. Chung, and J. W. Pennebaker, “Counting little words in big data: The psychology of communities, cultures, and history,” Social cognition and communication, 2012
[36] 黃金蘭, 林以正, 謝亦泰, and 程威銓, “中文版 [語文探索與字詞計算] 詞典之建立,” 中華心理學刊, vol. 54, no. 2, pp. 185-201, 2012.
[37] R. Agrawal, and R. Srikant, “Fast algorithms for mining association rules,” In Proceedings of the 20th International Conference on Very Large Data Bases,(VLDB), , September 1994, vol. 1215, pp. 487-499.
[38] E. Mower , M. J. Mataric, and S. Narayanan, “A framework for automatic human emotion classification using emotion profiles,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 19, no. 5, pp. 1057-1070, 2011.
[39] E. Belogay, C. Cabrelli, U. Molter, and R. Shonkwiler, “Calculating the Hausdorff distance between curves,” Information Processing Letters, vol. 64, no. 1, pp. 17-22, 1997.
[40] J. H. Kim, “Multiple face segmentation and tracking based on Robust Hausdorff distance matching,” Journal of Applied Sciences, vol. 5, no. 4, pp. 740-744, 2005.