摘要(英) |
In the research of semantic sentiment analysis, it will normally use some factor rules such as the utilization of emotional keywords and the emotional rules defined manually to increase the accuracy. Because of the demand for large amounts of data and the training take lots of time, these manual factors will usually make the construction of system unportable and decrease efficiency. In this thesis, based on the above demands, we propose a semantic sentiment analysis system, and it also have better quality and increase efficiency.
The system structure of this thesis is organized as follows. First, the data training: It is the research of emotion and emotion psychology. According to the linguistic definition such as HowNet and CKIP technical report, we could make the emotional rules to generate the sparse representation characteristic, and build the sparse representation dictionary. By solved the sparse coefficient, return the dictionary and coefficient of two categories to original vector respectively. Then calculate the error with original vector, the dependent category which is obtain minimum error. Second, the input topic and the obtainment of comments: It present how to get the comments of the hot topic in the internet forum. Finally, the data classification: we will analyze the accuracy of classified topics by the result of data training. Besides, the experimental results will identify the hot topic as the implementation of semantic classification models. |
參考文獻 |
[1] 中研院中文斷詞系統, “http://ckipsvr.iis.sinica.edu.tw/”.
[2] JIEBA, “https://github.com/fxsjy/jieba”.
[3] Stanford Word Segmenter, “http://nlp.stanford.edu/software/segmenter.shtml”.
[4] 曾元顯, 文件主題自動分類成效因素探討, 中國圖書館學會會報,第68期,頁62-83, 2002.
[5] 黃翊軒, “本體論為基之智慧型專利文件分類方法論研究”, 國立清華大學工業工程與工程管理學系碩士論文, 2007.
[6] wiki, “TF-IDF。https://zh.wikipedia.org/wiki/TF-IDF”.
[7] 王光耀, “基於稀疏表示之語者辨識之研究”, 國立中央大學資訊工程學系碩士論文, 2013.
[8] W. M. Campbell, J. P. Campbell, D. A. Reynolds, E. Singer, and P. A. Torres-Carrasquillo, “Support vector machines for speaker and language recognition,” Comput. Speech Lang., vol. 20, pp. 210–229, 2006.
[9] LIBSVM. http://www.csie.ntu.edu.tw/~cjlin/libsvmH. Accessed January, 2011.
[10] Ma, C. M., Yang, W. S., & Cheng, B. W. (2014). How the Parameters of K-nearest Neighbor Algorithm Impact on the Best Classification Accuracy: In Case of Parkinson Dataset. Journal of Applied Sciences, 14(2), 171-176
[11] R-SHINY統計分析平台“http://statisticprojct.weebly.com/2970235542.html”.
[12] Jia-Ching Wang et al. , "Speech Emotion Verification Using Emotion Variance Modeling and Discriminant Scale-Frequency Maps," IEEE Transactions on Audio, Speech and Language Processing,, (accepted for publication) (SCI)
[13] JavaScript Object Notation, “http://www.json.org/”.
[14] 董振東, “知網。http://www.keenage.com/html/c_index.html”, 1988.
[15] J. A. Russell & Pratt, “A description of the affective quality attributed to environments”, Journal of Personality and Social Psychology, 38(2), 311-322, 1980.
[16] R. J. Larson and E. Diener ,“Promises and Problems with the Circumplex Model of Emotion”, Review of Personality and Social Psychology: Emotion (Vol. 13, p. 31), 1992.
[17] J. Posner , J. A. Russell , B. S. Peterson ,“The circumplex model of affect: An integrative approach to affective neuroscience, cognitive development, and psychopathology”, Development and psychopathology,17(03), 715-734, 2005.
[18] 林宇中, “基於語意內容分析之情緒分類系統”, 國立成功大學資訊工程系碩士論文, 2003.
[19] 黃信華, “FACEBOOK塗鴉牆文本分析情緒文字的關係”, 國立台南大學數位科技學習系碩士論文, 2003.
[20] 王韋堯、黃詩珮、劉怡寧, “消費品廣告設計之情緒效價與喚起分析”, 設計學報,17(3),P.45-P.67, 2012.
[21] 王瀞誼, “衡量分類關聯規則的新方法”, 國立高雄大學電機工程研究所碩士論文, 2007.
[22] H. Chauhan, A.Chauhan, (2014). "Implementation of the Apriori algorithm for association rule mining" Compusoft 3.4 699-701.
[23] A. Chawla, K. S. Dhindsa, (2014). "Implementation of Association Rule Mining using Reverse Apriori Algorithmic Approach" International Journal of Computer Applications, 93.8 |