網路快速的發展造就了社交網路溝通平台的興起，而部落格就是其中具有代表性的溝通平台之一。部落格上，使用者會對自己所使用過的商品寫下評論，其中包含商品特徵、意見與情緒等，有些使用者會更進一步寫出想要的購物需求為何，但大多數的使用者並沒有寫出來，而部落格廣告也沒有針對使用者需求提供適合的廣告。目前就我們所知還沒有其他方法或系統透過應用程式針對文章找出符合使用者的購物需求，因此我們提出了購物需求推論模型。
購物需求推論模型包含了三個子模型，分別是商品模型、評論模型和需求模型，分別用來辨識商品、評論與提取購物需求。其中我們在評論中利用到了三類商品特徵，分別為品牌、品質與價格，而意見則依照特徵類別的不同有了正向意見類別與負向意見類別，情緒則分成正向情緒類別與負向情緒類別。
最後實驗部分顯示我們在辨識商品與評論分別有七成與六成以上的正確率，提出來的購物需求推論模型其精確值有達到五成以上，表示我們提出來的方法能有效的找出使用者的購物需求。

The rapid growth of internet results in the pervasive use of social communication platforms. One of the representative platforms is blog. On the blog, bloggers usually write down the comments containing product feature, opinion and emotion after purchasing certain products. A few bloggers write down what they want to buy in the future, but most bloggers do not. At present, advertisings offered by blog are not corresponding to bloggers’ merchandise need. According to our investigation, no other methods or systems are developed to find the bloggers’ merchandise need from blog posts, therefore, we propose Merchandise-Need Inference Model to tackle this problem.
Merchandise-Need Inference Model contains three sub-models, including product model, comment model and need model which are used to identify the product, the comment and extract blogger’ merchandise need. For the comment model, we propose three product features, including brand, quality and price. We divided opinion terms into two types of positive opinion and negative opinion, and emotional terms are also divided into positive and negative emotion terms.
Finally, experiments show that product identification are over 70% accuracy rate and comment identification are over 60% accuracy rate. Merchandise-Need Inference Model achieves over 50% precision for extracting blogger’ merchandise need.

1. Hui Yang, Bin Yang, Xu Zhou, Chunguang Zhou, Zhe Wang and Zhou Chai. Community discovery and sentiment mining for Chinese BLOG. In Proc. of FSKD, pp.1740-1745, 2010.
2. Yeha Lee, Hun-young Jung, Woosang Song and Jong-Hyeok Lee. Mining the Blogosphere for Top News Stories Identification. In Proc. of SIGIR'10, pp.395-402, 2010.
3. Keun Chan Park, Yoonjae Jeong and Sung Hyon Myaeng. Detecting Experiences from Weblogs. In Proc. of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 1464-1472, 2010.
4. Khalid El-Arini, Gaurav Veda, Dafna Shahaf, and Carlos Guestrin. Turning down the noise in the blogosphere. In Proc. of KDD'09, 2009.
5. Minqing Hu and Bing Liu. Mining and summarizing customer reviews. In Proc. of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 168–177, 2004.
6. Minqing Hu and Bing Liu. Mining Opinion Features in the Customer Reviews. In Proc. of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, August 22-25, 2004.
7. Satoshi Morinaga , Kenji Yamanishi , Kenji Tateishi and Toshikazu Fukushima. Mining product reputations on the Web. In Proc. of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, July 23-26, 2002.
8. Kushal Dave , Steve Lawrence and David M. Pennock. Mining the peanut gallery: opinion extraction and semantic classification of product reviews. In Proc. of the 12th international conference on World Wide Web, May 20-24, 2003.
9. Peiliang Tian, Yuanchao Liu, Ming Liu and Shanzong Zhu. Research Of Product Ranking Technology Based On Opinion Mining. In Second International Conference on Intelligent Computation Technology and Automation, pp. 239-243, 2009.
10. Steffen Rendle, Christoph Freudenthaler and Lars Schmidt-Thieme. Factorizing personalized Markov chains for next-basket recommendation. In Proc. of the 19th International Conference on World Wide Web, pp. 811–820, 2010.
11. Ana-Maria Popescu and Oren Etzioni. Extracting Product Features and Opinions from Reviews. In Proc. of HLT-EMNLP, 2005.
12. Rayid Ghani, Katharina Probst, Yan Liu, Marko Krema and Andrew Fano. Text Mining for Product Attribute Extraction. In Proc. of SIGKDD, pp.41-48, 2006.
13. Javier Parapar, Jorge López-Castro and Alvaro Barreiro. Blog snippets: a comments-biased approach. In Proc. of SIGIR'10, ACM, pp. 711-712, 2010.
14. Shima Gerani, Mark J. Carman and Fabio Crestani. Proximity-Based Opinion Retrieval. In Proc. of SIGIR'10, ACM, pp. 403-410, 2010.
15. Tengfei Ma and Xiaojun Wan. Opinion Target Extraction in Chinese News Comments. In The 23rd International Conference on Computational Linguistics, 2010.
16. Bing Liu , Minqing Hu and Junsheng Cheng. Opinion observer: analyzing and comparing opinions on the Web. In Proc. of the 14th international conference on World Wide Web, May 10-14, 2005.
17. Qi Su, Xinying Xu, Honglei Guo, Zhili Guo, Xian Wu, Xiaoxun Zhang, Bin Swen and Zhong Su. Hidden Sentiment Association in Chinese Web Opinion Mining. In Proc. of WWW’08, pp. 959-968, 2008.
18. Wei Jin and Hung Hay Ho. A Novel Lexicalized HMM-based Learning Framework for Web Opinion Mining. In Proc. of the 26th Annual International Conference on Machine Learning, 2009.
19. Michael Gamon, Anthony Aue, Simon Corston-Oliver, and Eric Ringger. Pulse: Mining customer opinions from free text. In Proc. of the International Symposium on Intelligent Data Analysis, number 3646 in Lecture Notes in Computer Science, pp. 121-132, 2005.
20. Giambattista Amati, Giuseppe Amodeo, Valerio Capozio, Carlo Gaibisso and Giorgio Gambosi. On performance of topical opinion retrieval. In Proc. of SIGIR'10, pp.777-778, 2010.
21. Yue Lu and Chengxiang Zhai. Opinion integration through semi-supervised topic modeling. In Proc. of 2008 International WWW Conference, pp. 121-130, 2008.
22. Seung-Wook Lee , Jung-Tae Lee , Young-In Song and Hae-Chang Rim. High Precision Opinion Retrieval using Sentiment-Relevance Flows. In Proc. of SIGIR'10, 2010.
23. Nozomi Kobayashi, Kentaro Inui, Yuji Matsumoto, Kenji Tateishi and Toshikazu Fukushima. Collecting Evaluative Expressions for Opinion Extraction. In Proc. of IJCNLP, pp. 596-605, 2005.
24. Giuseppe Attardi and Maria Simi. Blog Mining through Opinionated Words. In Proc. of TREC, 2006.
25. Gilad Mishne and Natalie Glance. Leave a Reply : An ANalysis of Weblog Comments. In Proc. of WWW'06, pp. 22-26, 2006.
26. Xiaochuan Ni, Gui-Rong Xue, Xiao Ling, Yong Yu and Qiang Yang. Exploring in the Weblog Space by Detecting Informative and Affective Articles. In Proc. of the 16th international conference on World Wide Web, pp. 281-290, 2007.
27. Gilad Mishne and Natalie Glance. Predicting Movie Sales from Blogger Sentiment. In AAAI 2006 Spring Symposium on Computational Approaches to Analysing Weblogs, 2006.
28. C.Yang, K.H. Lin, and H.Chen. Emotion Classification Using Web Blog Corpora. In Proc. of the IEEE/WIC/ACM International Conference on Web Intelligence, pp. 275-278, 2007.
29. Fazel KESHTKAR and Diana Inkpen. Using Setiment Orientation Features for Mood Classification in Blogs. In Proc. of the IEEE International Conference on Natural Language Processing and Knowledge Engineering, 2009.
30. Changhua Yang, Kevin Hsin-Yih Lin, and Hsin-Hsi Chen. Building emotion lexicon from weblog corpora. In Proc. of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions, 2007.
31. Changqin Quan and Fuji Ren. Construction of a Blog Emotion Corpus for Chinese Emotional Expression Analysis. In Proc. of the 2009 Conference on Empirical Methods in Natural Language Processing, pp. 1446-1454, 2009.
32. Yan Sun, Changqin Quan and Fuji Ren. Analysis on Degree Words for Chinese Emotion Expressions Based on Syntactic Parse and Rules. In Proc. of the IEEE International Conference on Natural Language Processing and Knowledge Enginerring, pp.562-567, Dalian, Sep. 2009.
33. John Lafferty, Andrew McCallum and Fernando Pereira. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Intl. Conf. on Machine Learning, 2001.
34. Yejin Choi, Claire Cardie, Ellen Riloff and Siddharth Patwardhan. Identifying Sources of Opinions with Conditional Random Fields and Extraction Patterns. In Proc. of HLT/EMNLP, 2005.
35. G.B. Sproles and E.L. Kendall. A methodology for Profiling Consumers' Decision-Making Styles. The Journal of Consumer Affairs, 20, pp.267-279, 1986.
36. Gerard M. Salton. A Theory of Indexing. Regional Conference Series Application Mathematics, Society for Industrial and Applied Mathematics, 1975.
37. Gerard M. Salton and Michael J. McGill. An introduction to modern information retrieval. 1983.
38. 林清河、施坤壽、許家銘（2001）。消費者決策型態與價值觀之研究─臺灣地區大學生之實證研究。國家科學委員會研究彙刊：人文及社會科學，十一卷一期，016-029。
39. 江亙松（2009）。文章標題的重要性。理財周刊，452。
40. 廖顯忠，「分析隱含於部落格文章的事件、情緒與需求」，國立成功大學資訊工程所碩士論文，2010。