現代人不免會遭遇到人生的困境與難關，在生活與學習的過程中卻鮮少教導與探討這些問題，除非主動尋求相關人員幫助或找相關書籍閱讀，多數人有可能使用消極的態度解讀遇上的困境與難關，這些態度往往解決不了事情，反而使問題更加擴大。
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。我們在這邊專注於使用者在文章中提到煩惱的部分，我們觀察到，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煩惱事件(harass event)，根據煩惱事件會引發出的情緒，我們在此把其稱為煩惱情緒(harass emotion)。根據煩惱事件、煩惱情緒會觸發煩惱需求(harass need)。最後我們會根據煩惱需求提供多個解答(solutions)給使用者，使其解決生活中的問題。這邊考慮到可信度的問題，於是我們想到的解法為使用書籍去做為解答，這樣可信度會高於一般網頁。
我們從痞客邦(PIXNET)收集了大量的部落格文章，用以觀察、訓練、和實驗，並且利用中央研究院的CKIP斷詞系統做文章的斷詞處理，然後可以根據我們訓練出來的模型去萃取出部落格文章的特徵，然後藉由這些特徵提供適當的解答。
在解答方面，因為無法取得書籍的完整內容，所以我們從線上書店博客來‎收集書籍的相關資訊，包括書籍介紹，與使用者評論…等作為作為推薦解答的依據。
實驗結果證明，我們的系統能有效找出使用者的煩惱需求，且能推薦有效的書籍作為解答幫助使用者解決生活上的難題。

Modern humans inevitably encounter difficulties and frustrations of life, but rarely teach and address these issues in the process of living and learning. Unless the initiative to seek help or find the relevant books to read, most people may use negative attitude to interpret difficulties and frustrations encountered. These attitudes often could not resolve the matter, but to make the issue even more to expand.
The rapid development of the Internet led to the rise of many social platform networking, blog is one of them. Blogs provide Internet users to communicate with each other to achieve the effect of text information exchange. We are here to focus on the part of the users who write harass in their blog articles. We observed that the user when writing the article will be a major Subject to represent the article. Here we call it harass event. According to the harass event would give rise to emotions, we are here to call it harass emotion. Harass event and harass emotion can trigger harass need, and finally we will provide multiple solutions based on harass need to the user to solve problems in life. Taking into account the issue of credibility, we use books as solutions.
We think in contrast to the pages, books have higher confidence.
We collect blog articles form PIXNET. We use these articles to do observation、training and testing. We also use Chinese segmentation and tagging tool to segment blog articles. And then, we can extract features of blog articles. Then, we can use these features to provide suitable solutions.
In part of solutions, we cannot get the complete contents of the book. Therefore, we collect book information from online bookstore, including book introduction, user comment, etc. we use book information as a basis for the recommended solutions.
Experimental results show that our method can effectively identify user's need harass need. Our method also can recommend books as effective solutions to help users solve problems in life.

[1] X. Ni, G.-R. Xue, X. Ling, Y. Yu, and Q. Yang, "Exploring in the weblog space by detecting informative and affective articles," in Proceedings of the 16th international conference on World Wide Web, 2007, pp. 281-290.
[2] C. C. Chen and M. C. Chen, "TSCAN: A content anatomy approach to temporal topic summarization," Knowledge and Data Engineering, IEEE Transactions on, vol. 24, pp. 170-183, 2012.
[3] A. Sun and M. Hu, "Query-guided event detection from news and blog streams," Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on, vol. 41, pp. 834-839, 2011.
[4] E. Lloret and M. Palomar, "Text summarisation in progress: a literature review," Artificial Intelligence Review, vol. 37, pp. 1-41, 2012.
[5] C.-Y. Teng and H.-H. Chen, "Event Detection and Summarization in Weblogs with Temporal Collocations," in LREC, 2008.
[6] Y.-H. Yang and H. H. Chen, "Machine recognition of music emotion: A review," ACM Transactions on Intelligent Systems and Technology (TIST), vol. 3, p. 40, 2012.
[7] Y.-P. Lin, Y.-H. Yang, and T.-P. Jung, "Fusion of electroencephalographic dynamics and musical contents for estimating emotional responses in music listening," Frontiers in neuroscience, vol. 8, 2014.
[8] S. Feng, D. Wang, G. Yu, W. Gao, and K.-F. Wong, "Extracting common emotions from blogs based on fine-grained sentiment clustering," Knowledge and information systems, vol. 27, pp. 281-302, 2011.
[9] C. Quan 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, pp. 1446-1454.
[10] M. Feidakis, T. Daradoumis, S. Caballe, J. Conesa, and D. Gañán, "A Dual-Modal System that Evaluates User's Emotions in Virtual Learning Environments and Responds Affectively," J. UCS, vol. 19, pp. 1638-1660, 2013.
[11] G.-H. Luo, J.-c. Liu, and S.-M. Yuan, "A Two-Layer SVM Classification Mechanism for Chinese Blog Article," in Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), 2011 International Conference on, 2011, pp. 9-15.
[12] D. Das and S. Bandyopadhyay, "Emotions on Bengali blog texts: role of holder and topic," in Advances in Social Networks Analysis and Mining (ASONAM), 2011 International Conference on, 2011, pp. 587-592.
[13] S. Chenye, L. Jianhua, C. Jieyuan, and C. Xiuzhen, "Chinese SNS blog classification using semantic similarity," in Computational Aspects of Social Networks (CASoN), 2013 Fifth International Conference on, 2013, pp. 1-6.
[14] W.-H. Lu and Y.-S. Chang, "Effective Blog Advertising by Understanding Blogger’s Emotions & Needs."
[15] Y. Zhang, M. Zhang, Y. Liu, and S. Ma, "Improve collaborative filtering through bordered block diagonal form matrices," in Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval, 2013, pp. 313-322.
[16] N. Pappas and A. Popescu-Belis, "Sentiment analysis of user comments for one-class collaborative filtering over TED talks," in Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval, 2013, pp. 773-776.
[17] H.-S. Park, J.-O. Yoo, and S.-B. Cho, "A context-aware music recommendation system using fuzzy bayesian networks with utility theory," in Fuzzy systems and knowledge discovery, ed: Springer, 2006, pp. 970-979.
[18] H.-C. Chen and A. L. Chen, "A music recommendation system based on music data grouping and user interests," in Proceedings of the tenth international conference on Information and knowledge management, 2001, pp. 231-238.
[19] T. Bogers, "Movie recommendation using random walks over the contextual graph," in Proc. of the 2nd Intl. Workshop on Context-Aware Recommender Systems, 2010.
[20] G. Arora, A. Kumar, G. S. Devre, and A. Ghumare, "MOVIE RECOMMENDATION SYSTEM BASED ON USERS’SIMILARITY," International Journal of Computer Science and Mobile Computing, vol. 3, pp. 765-770, 2014.
[21] C.-N. Ziegler, S. M. McNee, J. A. Konstan, and G. Lausen, "Improving recommendation lists through topic diversification," in Proceedings of the 14th international conference on World Wide Web, 2005, pp. 22-32.
[22] H. Ma, I. King, and M. R. Lyu, "Learning to recommend with social trust ensemble," in Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval, 2009, pp. 203-210.
[23] O. Phelan, K. McCarthy, and B. Smyth, "Using twitter to recommend real-time topical news," in Proceedings of the third ACM conference on Recommender systems, 2009, pp. 385-388.
[24] P.-M. Su, "Predicting Web User’s Tendency of Depression Using Event-Driven Negative Emotion Model," 2012.
[25] H. Li, Z. Cai, A. C. Graesser, and Y. Duan, "A comparative study on English and Chinese word uses with LIWC," in Twenty-Fifth International FLAIRS Conference, 2012.
[26] L.-W. Ku, Y.-T. Liang, and H.-H. Chen, "Opinion Extraction, Summarization and Tracking in News and Blog Corpora," in AAAI spring symposium: Computational approaches to analyzing weblogs, 2006.
[27] 許耀仁 and 王莉莉, 零阻力的黃金人生：清理內在的瑟多納釋放法, 2010.