Airbnb是目前在住宿業裡最成功的共享經濟平台代表。雖然評論系統的建立讓每位房客留下體驗後的評論對未來預計入住的旅客有很大的幫助，但是長久下來累積的大量文字資訊，卻也同時提高了房屋挑選上的困難，想要經由過往的評論找到適合的房屋所需耗費的心力比以往更多。
在本篇論文中，我們以LDA主題模型為基礎建立Airbnb個人化推薦系統。用主題分布的方式呈現每間房屋的特色，同時也透過房客的住宿紀錄建立每位房客各自的主題分布，以代表每位房客的偏好。透過計算房客和房屋之間的主題相似度降冪產生推薦清單，推薦數個該房客可能喜愛的房屋。
在實驗階段，我們透過召回率(Recall)衡量推薦系統的表現。首先以LDA為基礎的方法和現行常見方法進行比較，以及比較不同文字資訊作為來源的推薦系統表現如何。最後實驗結果顯示，資料來源同時採用房客評論和留言分數都有助於我們以LDA為基礎的系統推薦表現。

Airbnb is one of the most successful sharing economy platforms in the hospitality industry. Although the availability of large-scale reviews can be beneficial but it is more difficult in the decision-making process, because of the huge amount of reviews which make guests confused in selecting the best possible and suitable properties.
In this thesis, we propose a personalized recommender system by applying LDA to extract latent topics of textual resource of each property and use the probability of topic distribution to represent the features of each property. Further, construct guest profile based on guest’s historical records in order to realize guest preference. Finally, for each candidate property, we consider the profiles of property and guest to estimate a sorted recommend list for the guest.
For the evaluation, we adopt Recall to evaluate the recommendation performance. The experimental result shows that our LDA-based model performs better than the baseline. Afterwards, we compare the performance among different textual information which shows the review and rating score are appropriate resource for the property representation and guest preference on the LDA-based personalized recommender system.

CHAPTER 1-Introduction 1
1.1. Background and Motivation 1
1.2. Results and Contribution 5
1.3. Overall Architecture 6
CHAPTER 2-Literature Review 7
2.1. Content-Based Recommender Systems 7
2.2. Latent Dirichlet Allocation 8
CHAPTER 3-Methodology 10
3.1. Research Process 10
3.2. Data Collection 13
3.3. Data Preprocessing 14
3.4. Property Representation 17
3.5. Guest Profile Generation 19
3.6. Recommend Properties to Guest 22
CHAPTER 4-Empirical Evaluation 24
4.1. Dataset description 25
4.2. Experimental Settings 27
4.3. Evaluation metric 28
4.4. Result and discussion 30
CHAPTER 5-Conclusion and Future work 35
References 37

[1] G.Quattrone, D.Proserpio, D.Qsuercia, L.Capra, and M.Musolesi, “Who Benefits from the ‘Sharing’ Economy of Airbnb?,” Proc. 25th Int. Conf. World Wide Web, pp. 1385–1393, 2016.s
[2] F.Hawlitschek, T.Teubner, and C.Weinhardt, “Trust in the Sharing Economy,” Die Unternehmung, vol. 70, no. 1, pp. 26–44, 2016.
[3] E.Ert, A.Fleischer, and N.Magen, Trust and reputation in the sharing economy: The role of personal photos in Airbnb, vol. 55, no. August. 2016.
[4] D.Harrison, C.Coughlin, D.Hogan, and E.Shakun, “Airbnb’s Global Support to Local Economies: Output and Employment Prepared for Airbnb,” 2017.
[5] D.Guttentag, “Airbnb: disruptive innovation and the rise of an informal tourism accommodation sector,” Curr. Issues Tour., vol. 18, no. 12, pp. 1192–1217, Dec.2015.
[6] R.Botsman and R.Rogers, “Beyond zipcar: Collaborative consumption,” Harvard Business Review, vol. 88, no. 10. pp. 15, 2010.
[7] N.Hu, J.Zhang, and P. A.Pavlou, “Overcoming the J-shaped distribution of product reviews,” Commun. ACM, vol. 52, no. 10, pp. 144–147, 2009.
[8] G.Zervas, D.Proserpio, and J. W.Byers, “The Rise of the Sharing Economy： Estimating the Impact of Airbnb on the Hotel Industry,” Proc. Sixt. ACM Conf. Econ. Comput. - EC ’15, pp. 637–637, 2015.
[9] M.Hu and B.Liu, “Mining and summarizing customer reviews,” Proc. 2004 ACM SIGKDD Int. Conf. Knowl. Discov. data Min. - KDD ’04, p. 168, 2004.
[10] S.Brody, “An Unsupervised Aspect-Sentiment Model for Online Reviews,” Comput. Linguist., no. June, pp. 804–812, 2010.
[11] O.Phelan, K.McCarthy, M.Bennett, and B.Smyth, “On using the real-time web for news recommendation & discovery,” in Proceedings of the 20th international conference companion on World wide web - WWW ’11, 2011, p. 103.
[12] R. J. Mooney and L. Roy and R. J. M. and L.Roy, “Content-based book recommendation using learning for text categorization,” Proc. fifth ACM Conf. Digit. Libr., no. June, pp. 195–204, 1999.
[13] K. D.Bollacker, S.Lawrence, and C. L.Giles, “CiteSeer : An Autonomous Web Agent for Automatic Retrieval and Identification of Interesting Publications,” in Proceedings of the 2nd International Conference on Autonomous Agents, 1998, pp. 116–123.
[14] H.Mak, I.Koprinska, and J.Poon, “INTIMATE: A Web-based movie recommender using text categorization,” in Proceedings - IEEE/WIC International Conference on Web Intelligence, WI 2003, 2003, pp. 602–605.
[15] A.Levi, O.Mokryn, C.Diot, and N.Taft, “Finding a needle in a haystack of reviews,” Proc. sixth ACM Conf. Recomm. Syst. - RecSys ’12, p. 305, 2012.
[16] D.Blei and A.Ng, “Latent dirichlet allocation,” JMLR, vol. 3, pp. 993–1022, 2003.
[17] K.Tu, B.Ribeiro, D.Jensen, D.Towsley, B.Liu, H.Jiang, X.Wang, “Online Dating Recommendations: Matching Markets and Learning Preferences,” Proc. 23rd Int. Conf. World Wide Web - WWW ’14 Companion, pp. 787–792, Jan.2014.
[18] T.VanLe, T.Nghia Truong, T.Vu Pham, T.VanLe, T. N.Truong, and T. V.Pham, “A Content-Based Approach for User Profile Modeling,” Proc. 8th Int. Work. Multi-disciplinary Trends Artif. Intell. - Vol. 8875, pp. 232–243, 2014.
[19] M.Pennacchiotti and S.Gurumurthy, “Investigating topic models for social media user recommendation,” Proc. 20th Int. Conf. companion World wide web - WWW ’11, p. 101, 2011.
[20] E. L. and E. K.Bird, Steven, Natural Language Processing with Python. O’Reilly Media Inc., 2009.
[21] R.Rehurek, R.Rehurek, and P.Sojka, “Software Framework for Topic Modelling with Large Corpora,” Proc. Lr. 2010 Work. NEW CHALLENGES NLP Fram., pp. 45--50, 2010.
[22] D.Lee, W.Hyun, J.Ryu, W. J.Lee, W.Rhee, and B.Suh, “An Analysis of Social Features Associated with Room Sales of Airbnb,” Proc. 18th ACM Conf. Companion Comput. Support. Coop. Work Soc. Comput. - CSCW’15 Companion, pp. 219–222, 2015.
[23] J.Franco, V.Kakar, J.Voelz, and J.Wu, “Effects of Host Race Information on Airbnb Listing Prices in San Francisco,” Working Paper, no. 47061, Mar.2013.
[24] T.Brants, F.Chen, and I.Tsochantaridis, “Topic-based document segmentation with probabilistic latent semantic analysis,” in Proceedings of the eleventh international conference on Information and knowledge management - CIKM ’02, 2002, p. 211.
[25] T.Brants, F.Chen, and A.Farahat, “A System for new event detection,” in Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval - SIGIR ’03, 2003, p. 330.
[26] Q.Ye, R.Law, B.Gu, and W.Chen, “The influence of user-generated content on traveler behavior: An empirical investigation on the effects of e-word-of-mouth to hotel online bookings,” Comput. Human Behav., vol. 27, no. 2, pp. 634–639, Mar.2011.
[27] F.Riahi, Z.Zolaktaf, M.Shafiei, and E.Milios, “Finding expert users in community question answering,” Proc. 21st Int. Conf. companion World Wide Web - WWW ’12 Companion, no. i, pp. 791–798, 2012.
[28] D.Kowald, S.Pujari, and E.Lex, “Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach,” WWW ’17 (26th Int. World Wide Web Conf., vol. 5, pp. 1401–1410, 2017.
[29] X.Tan, J. X.Huang, and A.An, “Ranking Documents Through Stochastic Sampling on Bayesian Network-based Models,” in Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR ’16, 2016, pp. 961–964.
[30] Murray Cox, “Inside AirBnB,” Inside AirBnB, 2017. [Online]. Available: http://insideairbnb.com/. [Accessed: 17-Jul-2017].
[31] Statista, “Chart: Which Cities Have The Most Airbnb Listings? | Statista,” 2016. [Online]. Available: https://www.statista.com/chart/5204/which-cities-have-the-most-airbnb-listing/. [Accessed: 17-Jul-2017].
[32] Q.Ye, R.Law, and B.Gu, “The impact of online user reviews on hotel room sales,” Int. J. Hosp. Manag., vol. 28, no. 1, pp. 180–182, 2009.
[33] P. C.Ng, J.She, M.Cheung, and A.Cebulla, “An images-textual hybrid recommender system for vacation rental,” Proc. - 2016 IEEE 2nd Int. Conf. Multimed. Big Data, BigMM 2016, pp. 60–63, 2016.
[34] P.Yang, H.Wang, H.Fang, and D.Cai, “Opinions matter: a general approach to user profile modeling for contextual suggestion,” Inf. Retr. Boston., vol. 18, no. 6, pp. 586–610, 2015.