隨著行動裝置的普及，人們對於上網的型態有了改變，根據google發佈智慧型手機行為的調查報告指出，國人對智慧型手機的依賴度高達81%，可想而知裡面記錄了大量關於使用者的個人的資訊，像是購物行為，瀏覽資料等等，我們希望透過行動裝置結合文字探勘的技術來對使用者做出個人化旅館的推薦

我們設計了一個APP讓使用者來瀏覽旅館評論，希望從中紀錄使用者正在觀看那些文章，並透過APP捲軸的位置去判斷使用者目前可能在觀看的文章段落以及利用頁面停留的時間去擷取出使用者可能感興趣的內容

接著利用文字探勘的技術，去對文字內容作處理，像是斷句、標詞性，除了利用lexicon based的方式找找出feature以及判斷句子的情緒分數，我們還利用Alchemy API來輔助我們判斷句子的情緒
為了要擷取出使用者對於旅館的偏好以及驗證我們推薦的績效，我們從Tripadvisor網站收集了台灣12個縣市，360間旅館共10690篇文章，並邀請了18位常常到旅館住宿的使用者來參與我們的實驗，我們使用Kendall’s tau b correlation以及Precision@N的方式來評估我們系統推薦的準確度

最後實驗結果顯示，不管是哪一種評估方式，我們的推薦系統比起Tripadvisor上面的推薦方式提供相對較好的推薦結果

With the advance of mobile devices, the ways people use Internet have changed enormously. Mobile devices are capable of recording users’ behavior, such as locations visited, frequent online shopping stores, browsing history, and so on. The aim of this study is to utilize users’ browsing data on mobile devices and subsequently applying text mining techniques to recommend hotels to users.

Specifically, we design and implement an APP that allows its user to browse hotel reviews and records every gesture the user has performed. We then identified a subset of hotel reviews that the given user have shown interests depending on the different kinds of gestures he/she has performed. Text mining techniques are subsequently applied to construct the interest profile of the user based on the review content.

We collect 10,690 reviews of 360 hotels in Taiwan. 18 users are recruited to use our proposed APP and participate in the experiment. Experimental result demonstrates that our system have better performance than other approaches.

CHAPTER 1-Introduction 1
1.1. Background 1
1.2. Motivation 3

CHAPTER 2-Related Work 5
2.1. Aspect-based Sentiment Analysis 5
2.2 Mobile Information Retrieval 7
2.3. Hotel Recommender Systems 8

CHAPTER 3 - Natural Language Processing Tools 10
3.1 Tokenization 10
3.2 Part of Speech Tagging 10
3.3 Dependency Parser 11
3.4 Dependency chains 12
3.5 Sentiment Analysis 13
3.6 External Corpus 14

CHAPTER 4 - The Approach 16
4.1 Skeleton of Our Approach 16
4.2 User Profile Identification 18
4.2.1 Gathering Browsing Reviews 18
4.2.2 Determining the content of lines 20
4.2.3 Feature Detection 22
4.2.4 Calculate Feature’s Weight 24
4.3 Sentiment Analysis 26
4.4 Producing Score 28
4.4.1 Review Score 28
4.4.2 Producing a Personalized Score for a Hotel 30

CHAPTER 5 - Evaluation 31
5.1 Dataset Description 31
5.2 Experiment Design 33
5.3 Experiment Result 36
5.3.1 Precision@N 36
5.3.2 Kendall’s tau b correlation 39
5.3.3 Roc Curve 40

Chapter 6 - Conclusion 47

References 49

LIST OF FIGURES
Figure 3 1 Example For Stanford Part of Speech Tagging 11
Figure 3 2 Example for Dependency Chains 12
Figure 4 1 Skeleton of the Approach 16
Figure 4 2UIScrollView contentOffset 19
Figure 4 3 Feature Detection Example 23
Figure 4 4 Weights of Individual Aspects 25
Figure 4 5 Review Score 29
Figure 4 6 Review Score 30
Figure 5 1 Number of Reviews by cities 32
Figure 5 2 Number of Reviews in Word Count 33
Figure 5 3 Mobile APP Screenshot 34
Figure 5 4 Experiment Website Screenshot 35
Figure 5 5 Example of Precision@5 37
Figure 5 6 Average precision@5 of the three methods 38
Figure 5 7 Average recall@5 of the three methods 39
Figure 5 8 Kendall’s tau b correlation 40
Figure 5 9 Top@5 Roc curve 44
Figure 5 10 Top@4 Roc curve 44
Figure 5 11 Top@3 Roc curve 45
Figure 5 12 Top@2 Roc curve 45
Figure 5 13 Top@1 Roc curve 46

LIST OF TABLES
Table 3 1 Feature List 15
Table 4 1 Log of User Movement 20
Table 5 1 Four kinds of relationship 41

1. Lee, J., D.-H. Park, and I. Han, The effect of negative online consumer reviews on product attitude: An information processing view. Electronic Commerce Research and Applications, 2008. 7(3): p. 341-352.

2. Sigala, M., Web 2.0, social marketing strategies and distribution channels for city destinations: Enhancing the participatory role of travelers and exploiting their collective intelligence. Information communication technologies and city marketing: Digital opportunities for cities around the world, 2009: p. 220-44.

3. Gretzel, U. and K.H. Yoo, Use and impact of online travel reviews. Information and communication technologies in tourism 2008, 2008: p. 35-46.

4. Adomavicius, G. and A. Tuzhilin, Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. Knowledge and Data Engineering, IEEE Transactions on, 2005. 17(6): p. 734-749.

5. Jannach, D., et al., Recommender systems: an introduction. 2010: Cambridge University Press.

6. Berka, T. and M. Plößnig. Designing recommender systems for tourism. 2004. ENTER 2004: 11th International Conference on Information Technology in Travel & Tourism.

7. Ricci, F., Mobile recommender systems. Information Technology & Tourism, 2010. 12(3): p. 205-231.

8. Saga, R., Y. Hayashi, and H. Tsuji. Hotel recommender system based on user's preference transition. in Systems, Man and Cybernetics, 2008. SMC 2008. IEEE International Conference on. 2008. IEEE.

9. Rashid, A.M., et al. Getting to know you: learning new user preferences in recommender systems. in Proceedings of the 7th international conference on Intelligent user interfaces. 2002. ACM.

10. Schein, A.I., et al. Methods and metrics for cold-start recommendations. in Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval. 2002. ACM.

11. Woerndl, W. and J. Schlichter. Introducing context into recommender systems. in Proceedings of AAAI Workshop on Recommender Systems in E-Commerce. 2007.

12. Hariri, N., et al., Context-aware recommendation based on review mining. General Co-Chairs, 2011: p. 27.

13. Adomavicius, G. and A. Tuzhilin, Context-aware recommender systems, in Recommender systems handbook. 2011, Springer. p. 217-253.

14. Pang, B. and L. Lee, Opinion mining and sentiment analysis. Foundations and trends in information retrieval, 2008. 2(1-2): p. 1-135.

15. Liu, B., Sentiment analysis and opinion mining. Synthesis Lectures on Human Language Technologies, 2012. 5(1): p. 1-167.

16. Jiang, L., et al. Target-dependent twitter sentiment classification. in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1. 2011. Association for Computational Linguistics.

17. Hu, M. and B. Liu. Mining opinion features in customer reviews. in AAAI. 2004.

18. Brody, S. and N. Elhadad. An unsupervised aspect-sentiment model for online reviews. in Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics. 2010. Association for Computational Linguistics.

19. Cruz, F.L., et al., ‘Long autonomy or long delay?’The importance of domain in opinion mining. Expert Systems with Applications, 2013. 40(8): p. 3174-3184.

20. Morita, M. and Y. Shinoda. Information filtering based on user behavior analysis and best match text retrieval. in Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval. 1994. Springer-Verlag New York, Inc.

21. Rodden, K., et al. Eye-mouse coordination patterns on web search results pages. in CHI'08 Extended Abstracts on Human Factors in Computing Systems. 2008. ACM.

22. Fox, S., et al., Evaluating implicit measures to improve web search. ACM Transactions on Information Systems (TOIS), 2005. 23(2): p. 147-168.

23. Church, K. and B. Smyth. Understanding the intent behind mobile information needs. in Proceedings of the 14th international conference on Intelligent user interfaces. 2009. ACM.

24. Huang, J. and A. Diriye, Web user interaction mining from touch-enabled mobile devices. Proceedings of HCIR 2012, 2012.

25. Adomavicius, G. and Y. Kwon, New recommendation techniques for multicriteria rating systems. Intelligent Systems, IEEE, 2007. 22(3): p. 48-55.

26. Fuchs, M. and M. Zanker, Multi-criteria ratings for recommender systems: an empirical analysis in the tourism domain. 2012: Springer.

27. Jannach, D., et al., Recommending hotels based on multi-dimensional customer ratings. 2012: na.

28. Ghose, A., P.G. Ipeirotis, and B. Li, Designing ranking systems for hotels on travel search engines by mining user-generated and crowdsourced content. Marketing Science, 2012. 31(3): p. 493-520.

29. Levi, A., et al. Finding a needle in a haystack of reviews: cold start context-based hotel recommender system. in Proceedings of the sixth ACM conference on Recommender systems. 2012. ACM.

30. Ahn, H., K.-j. Kim, and I. Han. Mobile advertisement recommender system using collaborative filtering: Mar-cf. in Proceedings of the 2006 conference of the Korea society of management information systems. 2006.

31. Klein, D. and C.D. Manning, Parsing and hypergraphs, in New developments in parsing technology. 2005, Springer. p. 351-372.

32. Pontiveros, F. and B. Borja, Opinion mining from a large corpora of natural language reviews. 2012.

33. Ding, X., B. Liu, and P.S. Yu. A holistic lexicon-based approach to opinion mining. in Proceedings of the 2008 International Conference on Web Search and Data Mining. 2008. ACM.