本論文提出並實作一個應用意見探勘的方法在中文電影評論語料上,系統自 動對電影做評分與網路上已有的電影評價來比較。本論文的主要貢獻如下:
1. 建立 226 部電影資料庫,資料庫包含評論內容、評論評價和電影網路評價。
2. 人工收集電影屬性詞並利用同義詞詞林將這些屬性詞擴充,最後我們將這些 電影屬性詞分成四種類別。
3. 我們利用標記語料建立意見詞詞性序列,並使用這些詞性序列擷取意見詞。
4. 建立專屬電影領域的意見詞及產生每個意見詞的分數。
5. 在意見詞分數方面,考慮副詞加強及否定詞反轉的效果。在中文語言句型方 面,提出句型結構來更準確地找出屬性詞與意見詞配對。
6. 比較系統自動產生每部電影總評分與網路上已有的電影評價。
在本論文的未來研究,有下列幾個方向:
1. 屬性詞自動化擷取及分類。
2. 在屬性詞分類方面,屬性詞不一定固定屬於一個類別而已,屬性詞可以同時 屬於不同類別並解決屬性詞語義歧義的問題。
3. 利用收集每部電影的意見詞,可以對電影加以分類。例如:電影常出現感動...
等意見詞,在這情況這部電影可能屬於劇情片。
4. 把電影評分系統應用在專家寫的電影評論,比較在不同語料、知識下的評分 效果。
39
參考文獻 參考文獻 參考文獻 參考文獻
[1] 梅家駒等編著,同義詞詞林,臺灣東華書局股份有限公司,1997 年 3 月 [2] 李振昌,李禦璽,陳信希,“中文文本人名辨識問題之研究”,第七屆計算語
言學研討會論文集,1994 年,pp.203- 222.
[3] NTUSD(National Taiwan University Semantic Dictionary) http://nlg18.csie.ntu.edu.tw:8080/opinion/pub1.html
[4] 古倫維,李佳穎,陳信希,“意見持有者辨識之研究”,中文計算語言學期刊,
2009年,第十四卷第四期
[5] CKIP,中央研究院中文斷詞系統,http://ckipsvr.iis.sinica.edu.tw/,2011年 [6] Li Zhuang, Feng Jing, and Xiao-Yan Zhu (2006), "Movie review mining and
summarization", In the Proceedings of the CIKM Conference
[7] X. Ding, B. Liu, and P. Yu (2008), "A Holistic Lexicon-Based Approach to Opinion Mining" , Proceedings of the first ACM International Conference on Web search and Data Mining (WSDM)
[8] Pimwadee Chaovalit and Lina Zhou(2005), "Movie Review Mining: a
Comparison between Supervised and Unsupervised Classification Approaches", Proceedings of the 38th Annual Hawaii International Conference on System Sciences (HICSS)
[9] Qiang Ye, Wen Shi, and Yijun Li(2006) ,"Sentiment Classification for Movie Reviews in Chinese by Improved Semantic Oriented Approach", Proceedings of the 39th Annual Hawaii International Conference on System Sciences (HICSS)
[10] 甯格致,賴昆棋,“基於網路社群之旅遊經驗及對應情境之情感意見分析研
究”,Proceedings of the 22nd Conference on Computational Linguistics and Speech Processing (ROCLING),2010 年
[11] Turney(2002), "Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews", Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 417-424 [12] Likun Qiu, Weishi Zhang, Changjian Hu, and Kai Zhao(2009), "SELC : A
Self-Supervised Model for Sentiment Classification", CIKM
[13] 陳立,“中文情感語意自動分類之研究”,國立臺灣師範大學資訊工程所碩士 論文,2010年
[14] Minqing Hu and Bing Liu(2004), "Mining and summarizing customer reviews", KDD, pp.168-177
[15] Oren Etzioni and Ana-Maria Popescu(2005), "Extracting product features and opinions from reviews", Proceedings of the conference on Human Language
40
Technology and Empirical Methods in Natural Language Processing(HLT) [16] Bing Liu, Minqing Hu, and Cheng Junsheng(2005), "Opinion Observer:
Analyzing and Comparing Opinions on the Web", 14th international conference on World Wide Web(www), pp. 342–351
[17] Marie-Catherine de Marneffe, Christopher D. Manning, and Christopher
Potts(2010) ,"“Was it good? It was provocative.”Learning the meaning of scalar adjectives", 48th Annual Meeting of the Association for Computational
Linguistics(ACL)
[18] Qi Su, Xinying Xu, Honglei Guo, Zhili Guo, XianWu, Xiaoxun Zhang, Bin Swen, and Zhong Su(2008), "Hidden Sentiment Association in Chinese Web Opinion Mining", 17th international conference on World Wide Web(WWW) [19] Binyang Li, Lanjun Zhou, Shi Feng, and Kam-Fai Wong(2010) ,"A Unified
Graph Model for Sentence-based Opinion Retrieval", 48th Annual Meeting of the Association for Computational Linguistics(ACL) , pp. 1367–1375
[20] Changli Zhang, Daniel Zeng, Jiexun Li, Fei-Yue Wang, and Wanli
Zuo(2009) ,"Sentiment Analysis of Chinese Documents: From Sentence to Document Level", Journal of the American Society for Information Science and Technology, pp.2474-2487
[21] Chih-Chung Chang and Chih-Jen Lin, LIBSVM : a library for support vector machines (2001), Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm [22] Corinna Cortes and Vladimir Vapnik (1995), "Support-Vector Networks",
Machine Learning, Vol. 20, pp. 273-297.
[23] 林宇中,“基於語意內容分析之情緒分類系統”,國立成功大學,碩士論文,
2003 年
[24] Niklas Jakob and Iryna Gurevych(2010) , "Using Anaphora Resolution to Improve Opinion Target Identification in Movie Reviews", Proceeding ACLShort '10 Proceedings of the ACL Conference Short Papers, USA [25] Ramanathan Narayanan, Bing Liu, and Alok Choudhary(2009). "Sentiment
Analysis of Conditional Sentences" , Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP-09), August 6-7, Singapore.
[26] Valentin Jijkoun, Maarten de Rijke, and Wouter Weerkamp(2010), "Generating Focused Topic-Specific Sentiment Lexicons", In Proceedings of ACL.
pp.585~594
[27] Wei Jin, Hung Hay Ho, and Rohini K. Srihari(2009), "OpinionMiner: A Novel Machine Learning System for Web Opinion Mining and Extraction", In
Proceedings of KDD, pp.1195-1204
41
[28] Lili Zhao and Chunping Li(2009), "Ontology Based Opinion Mining for Movie Reviews ", Lecture Notes in Computer Science, pp.204-214
[29] Kuat Yessenov and Saˇsa Misailovi´(2009) , "Sentiment Analysis of Movie Review Comments" , Massachusetts Institute of Technology
[30] Dan Fingal, Je_ Michels, and Jamie Nicolson(2004), "Summarizing Movie Reviews", Stanford University
[31] 朱嫣嵐,閔錦,周雅倩,黃萱菁,吳立德,“基於HowNet的詞彙語義傾向計 算”, 中文信息學報,上海,2006年
[32] Changli Zhang, Daniel Zeng, Jiexun Li, Fei-Yue Wang, Wanli Zuo(2009),
"Sentiment analysis of Chinese documents: From sentence to document level", JASIST, pp. 2474-2487
[33] Le Cuong Anh, Shimazu Akira. (2004), "High WSD Accuracy Using Naïve Bayesian Classifier with Rich Features", PACLIC 18, Waseda University, Tokyo, pp. 105-113
42
43
44
意義 50 過程 50 結尾 48 爆點 46 關係 46
對打 16 演戲 15 描述 15 刻 15 編排 15
主軸 4 故事性 4 床戲 4 營造 4 ending 3
45
46
47
48