網路快速的發展導致許多網路社交平台的興起，部落格就是其中之一。部落格提供了以網路使用者互相交流的方式來達到文字資訊交流的效果。我們發現到部落格使用者在撰寫文章時會以一個主要的主題來代表文章，在這邊我們把其稱為事件；根據文章的主題會引發出各種不同的情緒，在這邊我們把其稱為情緒；最後根據事件與情緒的關係觸發了需求，在這邊我們把其稱為需求。
基於部落格為文字社交的平台，當作者再撰寫文章時並沒有依照一定的規範去執行，而且文章的內容同時可能包含許多的事件、情緒與需求。也因此在文章中的事件、情緒與需求並不明確，因此我們在這邊提出了兩階段的做法來抽取出部落格文章的事件、情緒與需求。在第一階段部份我們提出了針對事件(Event)與需求(Need)部份作Candidate的選擇，在事件部份是以計算文章內所有可能事件的分數作為考量，每個事件的分數包含POS(Part of Speech) 分數、詞彙(Context)分數與標題(Title)分數；另外在Need的分數包含POS(Part of Speech)分數與詞彙(Context)分數。在第二階段部份我們提出了Emotion-based Event Need Suggesting Model，我們利用第一階段所選擇的事件候選以及需求候選再加上情緒的部份抽取出部落格文章的事件、情緒與需求，在情緒部分我們將部落格的情緒先做分類的動作，在這邊我們總共分為七類，分別是快樂(happy)、生氣(angry)、擔心(worry)、思考(think)、悲傷(sad)、害怕(scare)與驚嚇(frighten)，接著根據分類後的結果在去評估部落格文章的情緒，其實驗的正確性有達到72%，表示我們判斷文章的情緒是可行的；最後實驗部份顯示我們提出來的模型精確值有達到五成以上的結果，表示我們提出的方法能找出部落格文章的事件、情緒與需求。

The rapid development of Internet led to many communication platform rise, blog is the one which provide text information communicate by a way of web user communicate each other. We find that when blogger are write articles, they would use main topic to stand for article, we define Event. Event would cause various blogger’s feel, we define Emotion. Event and Emotion would cause blogger’s need, we define Need.
When bloggers are not follow same rule to write articles and have many Event, Emotion and Need, it led to Event and Emotion and Need are not clearly in blog articles. Our Work propose two stage method to extract blog article’s Event, Emotion and Need. We propose the work of Selecting Event Candidate and Selecting Need Candidate for Event and Need. At the part of Event Candidate Selecting, we calculate Event score for every event terms in test blog articles, and Event score include Event POS(Part of Speech) score, Event context Score and Event Title Score at first stage. Moreover, at the part of Need Candidate Selecting, we calculate Need score for every Need terms in test blog articles, and Need score include Need POS(Part of Speech) score, Need context Score. At the second stage we propose a Emotion-base Event Need Suggesting Model, we use Event Candidate and Need Candidate from first stage analysis and Emotion to extract blog article’s Event, Emotion and Need. Furthermore, we classify emotion terms to seven classes and detect blog article’s emotion, experiment result has reach 72% accuracy. Final experiment show that the precision of our model has reach upper 50%, result show that our proposed method can find the blog article, events, emotions and needs.

1.Cao, D., et al., Blog post and comment extraction using information quantity of web format, in Proceedings of the 4th Asia information retrieval conference on Information retrieval technology. 2008, Springer-Verlag: Harbin, China. p. 298-309.
2.Wang, C., et al. UNDERSTANDING CONSUMERS ATTITUDE TOWARD ADVERTISING. in Eighth Americas Conference on Information Systems. 2002.
3.Ni, X., et al. Exploring in the Weblog Space by Detecting Informative and Affective Articles. in www. 2007.
4.Lin, K.H.-Y., C. Yang, and H.-H. Chen, Emotion Classification of Online News Articles from the Reader's Perspective, in Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 01. 2008, IEEE Computer Society. p. 220-226.
5.Chen, C.C. and M.C. Chen, TSCAN: a novel method for topic summarization and content anatomy, in Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval. 2008, ACM: Singapore, Singapore. p. 579-586.
6.Kumaran, G. and J. Allan, Text classification and named entities for new event detection, in Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval. 2004, ACM: Sheffield, United Kingdom. p. 297-304.
7.Kuo, J.-J. and H.-H. Chen, Multidocument Summary Generation: Using Informative and Event Words. ACM Transactions on Asian Language Information Processing (TALIP), 2008. 7(1): p. 1-23.
8.Teng, C.-Y. and H.-H. Chen. Event Detection and Summarization in Weblogs with Temporal Collocations. 2006.
9.Wu, T.-L., et al., Interactive content presentation based on expressed emotion and physiological feedback, in Proceeding of the 16th ACM international conference on Multimedia. 2008, ACM: Vancouver, British Columbia, Canada. p. 1009-1010.
10.Lin, K.H.-Y. and H.-H. Chen, Ranking reader emotions using pairwise loss minimization and emotional distribution regression, in Proceedings of the Conference on Empirical Methods in Natural Language Processing. 2008, Association for Computational Linguistics: Honolulu, Hawaii. p. 136-144.
11.Bar-Ilan, J., An outsider's view on "topic-oriented blogging", in Proceedings of the 13th international World Wide Web conference on Alternate track papers & posters. 2004, ACM: New York, NY, USA. p. 28-34.
12.Leshed, G. and J.J. Kaye, Understanding how bloggers feel: recognizing affect in blog posts, in CHI '06 extended abstracts on Human factors in computing systems. 2006, ACM: Montréal, Québec, Canada. p. 1019-1024.
13.Melville, P., W. Gryc, and R.D. Lawrence, Sentiment analysis of blogs by combining lexical knowledge with text classification, in Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining. 2009, ACM: Paris, France. p. 1275-1284.
14.Yang, C., K.H.-Y. Lin, and H.-H. Chen, Emotion Classification Using Web Blog Corpora, in Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence. 2007, IEEE Computer Society. p. 275-278.
15.Hsu, C.-W., & Lin, C.-J. A comparison of methods for multi-class support vector machines. in IEEE. 2002: IEEE.
16.Quan, C. and F. Ren, Construction of a blog emotion corpus for Chinese emotional expression analysis, in Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3 - Volume 3. 2009, Association for Computational Linguistics: Singapore. p. 1446-1454.
17.He, B., et al., An effective statistical approach to blog post opinion retrieval, in Proceeding of the 17th ACM conference on Information and knowledge management. 2008, ACM: Napa Valley, California, USA. p. 1063-1072.
18.Macdonald, C., I. Ounis, and I. Soboroff, Is spam an issue for opinionated blog post search?, in Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval. 2009, ACM: Boston, MA, USA. p. 710-711.
19.Adar, E., et al., Why we search: visualizing and predicting user behavior, in Proceedings of the 16th international conference on World Wide Web. 2007, ACM: Banff, Alberta, Canada. p. 161-170.
20.Sun, A., M. Hu, and E.-P. Lim, Searching blogs and news: a study on popular queries, in Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval. 2008, ACM: Singapore, Singapore. p. 729-730.