臺灣博碩士論文加值系統

隨著網際網路的發展，消費者會在網路的論壇或部落格分享他們購買與使用產品的經驗，或者在購買前請教他人問題。分析這些消費者產生的內容 (Customer Generated Media，CGM) 已逐漸成為行銷或品牌經理瞭解消費者傾向的重要管道。
本研究利用意見資訊的擷取與意見傾向的判斷技術，分析 「Mobile01」 3C 論壇裡網路使用者對筆記型電腦所表達的意見之傾向。本系統首先透過意見單元，以結構化的方式擷取 3C 論壇文章內容中對產品的意見，再以人工建置的 Heuristic Rules 以及使用關聯式法則訓練出來的 Context Dependent Rules 來判斷意見單元的語意傾向。實驗結果顯示，對語意傾向判斷的整體 F1 可達 89.55%。最後，本研究再以直條圖和對應分析的方式呈現產品的口碑狀況，表達使用者對產品在價格、功能等方面的正負向定位。

With proliferation of the Internet, consumers frequently share their opinions shopping or product using experience on forums and blogs. They also consult others on the Internet before making buying decisions. The analysis of consumer-generated content (Customer Generated Media, CGM) has become an important channel for the marketing professionals to understand consumer preferences.
This study employs an integrated rule-based method to conduct opinion mining of Notebook products from local web forum, Mobile3C.
We first create heuristic rules to determine semantic orientation of context independent opinion units. Then we generate association rules to resolve context dependent cases with the help of human annotators.
Experimental results indicate that the proposed rule-based system can determine semantic orientation with a Macro-F1 of 89.55%. We also provide visual user interface based on correspondence analysis results to show overall product reputation.

書名頁 i
論文口試委員審定書 ii
授權書 iii
中文摘要 iv
英文摘要 v
誌謝 vi
目錄 vii
表目錄 ix
圖目錄 x
第一章、緒論 1
1.1. 研究動機 1
1.2. 研究目的 2
1.3. 論文架構 2
第二章、文獻探討 3
2.1. 網路意見探勘 3
2.2. CGM 文章格式 4
2.3. 意見資訊的擷取 5
2.3.1 意見單元的定義 6
2.3.2 基於詞性的意見擷取方式 7
2.3.3 基於詞庫的意見擷取方式 8
2.3.4 中文斷詞 9
2.4. 意見傾向的判斷 11
2.4.1 Rule-based Method 12
2.4.2 WordNet Exploring Method 14
2.4.3 PMI Method 15
2.5. 半自動標註 (Semi-Automated Tagging) 16
2.6. 關聯式規則之探勘 16
2.7. 對應分析介紹 18
第三章、研究方法 20
3.1 系統運作流程 20
3.2 網頁擷取與網頁剖析 21
3.3 意見單元的擷取 22
3.3.1 CGM Segmentation 23
3.3.2 Generate OP Units 29
3.4 意見單元的語意傾向判斷 34
3.4.1 Context Independent 34
3.4.2 Context Dependent 36
3.5 Orientation Determination 41
第四章、實驗評估 42
4.1. 實驗資料集 42
4.2. 實驗評估指標 42
4.3. 系統傾向判斷實驗評估 44
4.3.1 5-fold Cross Validation 實驗 44
4.3.2 語意傾向誤判分析 47
4.4. 實驗結果畫面呈現 50
第五章、結論與未來展望 55
5.1. 結論 55
5.2. 未來展望 56
參考文獻 57

[1]陳家倫，2001 『台灣宗教行動圖像的初步建構』，國立台灣大學社會學研究所博士論文。
[2]平震宇，2007 『一個適用於行動裝置的網頁搜尋結果分群系統之研究』，元智大學資訊管理研究所碩士論文。
[3]陳智威，2008 『一個中英文搜尋結果即時分群系統之研究』，元智大學資訊管理研究所碩士論文。
[4]Abbasi, A., Chen, H. and Salem, A. 2008. Sentiment analysis in multiple languages: Feature selection for opinion classification in Web forums. ACM Trans. Inf. Syst. (26:3), pp. 1-34.
[5]Agrawal, R. and Srikant, R. 1994. Fast Algorithms for Mining Association Rules. Proceedings of the 20th International Conference on VLDB.
[6]Benamara, F., Cesarano, C., Picariello, A., Reforgiato, D. and Subrahmanian, V.S. 2007. Sentiment Analysis: Adjectives and Adverbs are better than Adjectives Alone. Proceedings of ICWSM 07 International Conference on Weblogs and Social Media, pp. 203-206.
[7]Benzecri, J.P. 1992. Correspondence Analysis Handbook. Mercel Dekker.
[8]Dave, K., Lawrence, S., and Pennock, D. 2003. Mining the Peanut Gallery: Opinion Extraction and Semantic Classification of Product Reviews. Proceedings of the twelfth international conference on World Wide Web, pp. 519-528.
[9]Ding, X., Liu, B. and Yu, P. S. 2008. A holistic lexicon-based approach to opinion mining. Proceedings of the international conference on Web search and web data mining. Palo Alto, California, USA, ACM., pp. 231-240.
[10]Esuli, A. and Sebastiani, F. 2005. Determining the semantic orientation of terms through gloss classification. Proceedings of the 14th ACM international Conference on information and Knowledge Management. CIKM ''05. ACM, New York, NY, pp. 617-624.
[11]Esuli, A. and Sebastiani, F. 2006. Determining term subjectivity and term orientation for opinion mining. Proceedings of the Eleventh Conference on European Chapter of the Association for Computational Linguistics. European Chapter Meeting of the ACL. Association for Computational Linguistics. pp. 193-200.
[12]Fuketa, M.,Kadoya, Y.,Atlam, E.,Kunikata, T.,Morita, K.,Kashiji, S. and Aoe, J.-I. 2005. A method of extracting and evaluating good and bad reputations for natural language expressions. International Journal of Information Technology and Decision Making. (4:2), pp. 177-196.
[13]Greenacre, M.J. 1993. Correspondence analysis in practice. Lon-don: Academic Press.
[14]Hu, M. and Liu B. 2004. Mining and summarizing customer reviews. Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining. Seattle, WA, USA, ACM., pp. 168-177.
[15]Hu, M., and Liu, B. 2004. Mining Opinion Features in Customer Reviews. In Proceedings of Nineteenth National Conference on Artificial Intelligence. The AAAI Press, Menlo Park, CA, pp. 755-760.
[16]Kobayashi, N., Inui, K. and Matsumoto, Y. 2007. Opinion Mining from Web Documents: Extraction and Structurization. Information and Media Technologies (2:1), pp. 326-337.
[17]Lee, D., Jeong, O. and Lee, S. 2008. Opinion mining of customer feedback data on the web. Proceedings of the 2nd international conference on Ubiquitous information management and communication. Suwon, Korea, ACM, pp. 230-235.
[18]Li, M. and Zhang, L. 2008. Multinomial mixture model with feature selection for text clustering. Knowledge-Based Systems (21:7), pp. 704-708.
[19]Liu, B. 2007. Web Data Mining book.
[20]Liu, B., Hu, M. and Cheng, J. 2005. Opinion observer: analyzing and comparing opinions on the Web. Proceedings of the 14th international conference on World Wide Web. Chiba, Japan, ACM., pp. 342-351.
[21]Ma, W.Y. and Chen, K.J. 2003. Introduction to CKIP Chinese Word Segmentation System for the First International Chinese Word Segmentation Bakeoff. Proceedings of ACL, Second SIGHAN Workshop on Chinese Language Processing, pp: 168-171.
[22]Morinaga, S., Yamanishi, K., Tateishi, K. and Fukushima, T. 2002. Mining product reputations on the Web. Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 341-349.
[23]Popescu, A. and Etzioni, O. 2005. Extracting product features and opinions from reviews. Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing. Human Language Technology Conference. Association for Computational Linguistics, Morristown, NJ, pp.339-346.
[24]Scaffidi, C., Bierhoff, K., Chang, E., Felker, M., Ng, H. and Jin, C. 2007. Red Opal: Product-Feature Scoring from Reviews. Proceedings of the 8th ACM conference on Electronic commerce, pp. 182-191.
[25]Turney, P. D. 2001. Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews. Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. Annual Meeting of the ACL. Association for Computational Linguistics. Morristown, NJ, pp. 417-424.
[26]Yang, C. C. and Wong, Y. C. 2008. Mining consumer opinions from the web. Proceedings of the International Conference on Web Information Systems and Technologies. Funchal, Madeira, Portugal.
[27]Zaiane, O. R., and Antonie, M. L. 2002. Text Document Categorization by Term Association. Proceeding of the IEEE International Conference on Data Mining, pp. 19.
[28]Zheng, Z. and Srihari, R. 2003. Optimally combining positive and negative features for text categorization. Proceedings of the ICML''03 Workshop on Learning from Imbalanced Date Sets, available at http://www.site.uottawa.ca/~nat/Workshop2003/zheng.pdf.