臺灣博碩士論文加值系統

隨著分享照片及影片社群網站的興起，越來越多使用者分享他們的照片或影片給他們的家人及朋友。因此，在本研究中，我們提出了一個研究架構，透過照片分享網站中使用者產生的資料，推薦符合使用者興趣及時間需求的旅遊行程。首先，我們採用平均移動分群演算法，將所收集的地點分成地標，再將地標合併成區域。接著，我們採用隱含狄利克雷分佈模型，將具有相似主題的地標分在一起。然後，我們計算每個使用者到訪每個地標以及區域的偏好(分數)，在計算分數時，我們會考量到地標的熱門程度、地標跟使用者在主題上的相似程度，以及相似的使用者到訪地標的比例。最後，根據每個地標與區域的分數，我們提出一個有效率的演算法，推薦k個最高分數的旅遊行程給使用者。多數過往的研究皆以地標為單位來推薦行程，而我們的架構則以區域為單位來進行推薦，因此，可以避免推薦出會在區域間往返的繞路行程。這樣不僅可節省交通時間，也讓使用者有更多時間能到訪更多的地點。實驗結果顯示，我們的方法無論在推薦行程的平均分數或推薦的精確度都勝過Markov-Topic方法。我們所提出的架構，可幫助使用者們規劃理想的旅遊行程，並且針對不同型態的使用者，客製化合適的行程。

With the increasing popularity of photo and video sharing social networks, more and more people have shared their photos or videos with their family members and friends. Therefore, in this study, we propose a framework for recommending travel tours to meet user’s individual interest and time-awareness by using user-generated contents in a photo sharing social network. The proposed framework contains four phases. First, we cluster geotagged locations into landmarks, and further clusters these landmarks into areas by mean-shift clustering method. Second, we employ the Latent Dirichlet Allocation model to cluster together similar landmarks. Third, to recommend tours for a user, we compute the tendency (or score) of visiting each landmark by the landmark popularity, attraction of landmark to the user, and how many users similar to the user visit the landmark. Finally, based on the scores computed, we develop an efficient method to recommend top-k tours with highest scores for the user. Unlike most previous methods recommending tours landmark by landmark, our framework recommends tours area by area so that users can avoid going back and forth from one area to another and save plenty of time on transportation, which in turn can visit more landmarks. The experiment results show that our proposed method outperforms the Markov-Topic method in terms of average score and precision. Our proposed framework may help users plan their trips and customize a trip for each individual.

Table of Contents ... i
List of Figures ... ii
List of Tables ... iii
Chapter 1 Introduction ... 1
Chapter 2 Related Work ... 4
Chapter 3 Our Proposed Framework ... 7
3.1 Location clustering ... 8
3.2 Landmark and user characterization ... 8
3.3 Score of each landmark and area ... 11
3.4 Tour recommendation ... 14
Chapter 4 Experiment Results ... 19
4.1 Performance evaluation ... 20
4.2 Example tours ... 24
Chapter 5 Conclusions and Future Work ... 29
References ... 31

[1]D. M. Blei, A. Y. Ng, and M. I. Jordan, Latent Dirichlet allocation, Journal of Machine Learning Research, Vol. 3, pages 993–1022, 2003.
[2]D. Crandall, L. Backstrom, D. Huttenlocher, and J. Kleinberg, Mapping the world’s photos, Proceedings of the 18th International Conference on World Wide Web, pages 761–770, 2009.
[3]Y. Cheng, Mean shift, mode seeking, and clustering, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, No. 8, pages 790–799, 1995.
[4]Q. Hao, R. Cai, X. Wang, J. Yang, Y. Pang, and L. Zhang, Generating location overviews with images and tags by mining user-generated travelogues, Proceedings of the 17th ACM International Conference on Multimedia, pages 801–804, 2009.
[5]H.P. Hsieh, C.T. Li, and S.D. Lin, Exploiting large-scale check-in data to recommend time-sensitive routes, Proceedings of the ACM SIGKDD International Workshop on Urban Computing, pages 55–62, 2012.
[6]S. Jain, S. Seufert, and S. J. Bedathur, Antourage: Mining distance-constrained trips from Flickr, Proceedings of the 19th International Conference on World Wide Web, pages 1121–1122, 2010.
[7]R. Ji, Y. Gao, B. Zhong, H. Yao, and Q. Tian, Mining Flickr landmarks by modeling reconstruction sparsity, ACM Transactions on Multimedia Computing, Communications, and Applications, Vol. 7S, No. 1, pages 31.1–31.22, 2011.
[8]T. Kurashima, T. Iwata, T. Hoshide, N. Takaya, and K. Fujimura, Geo topic model: Joint modeling of user’s activity area and interests for location recommendation, Proceedings of the Sixth ACM International Conference on Web Search and Data Mining, pages 375–384, 2013.
[9]T. Kurashima, T. Iwata, G. Irie, and K. Fujimura, Travel route recommendation using geotags in photo sharing sites, Proceedings of the 19th ACM International Conference on Information and Knowledge Management, pages 579–588, 2010.
[10]T. Kurashima, T. Iwata, G. Irie, and K. Fujimura, Travel route recommendation using geotagged photos, Knowledge and Information Systems, Vol. 37, No. 1, pages 37–60, 2013.
[11]S. Lloyd, Least squares quantization in PCM, IEEE Transactions on Information Theory, Vol. 28, No. 2, pages 129–137, 1982.
[12]E. H.C. Lu, C.Y. Chen, and V. S. Tseng, Personalized trip recommendation with multiple constraints by mining user check-in behaviors, Proceedings of the ACM 20th International Conference on Advances in Geographic Information Systems, pages 209–218, 2012.
[13]X. Lu, C. Wang, J.-M. Yang, Y. Pang, and L. Zhang, Photo2trip: Generating travel routes from geo-tagged photos for trip planning, Proceedings of the ACM International Conference on Multimedia, pages 143–152, 2010.
[14]A. Mnih, and R. Salakhutdinov, Probabilistic matrix factorization, Proceedings of International Confrence on Advances in Neural Information Processing Systems, pages 1257–1264, 2007.
[15]A. Popescu, and G. Grefenstette, Deducing trip related information from Flickr, Proceedings of the 18th International Conference on World Wide Web, pages 1183–1184, 2009.
[16]A. Popescu, and G. Grefenstette, Mining user home location and gender from Flickr tags, Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media, pages 307–310, 2010.
[17]L. Santos, J. Coutinho-Rodrigues, C.H. Antunes, A web spatial decision support system for vehicle routing using Google Maps, Decision Support Systems, Vol. 51, No. 1, pages 1–9, 2011.
[18]B. Sarwar, G. Karypis, J. Konstan, and J. Riedl, Item-based collaborative filtering recommendation algorithms, Proceedings of the 10th ACM International Conference on World Wide Web, pages 285–295, 2001.
[19]S. Sra, and I. S. Dhillon, Generalized nonnegative matrix approximations with Bregman divergences, Proceedings of International Confrence on Advances in Neural Information Processing Systems, pages 283–290, 2005.
[20]X. Su, and T. M. Khoshgoftaar, A survey of collaborative filtering techniques, Advances in Artificial Intelligence, Vol. 2009, pages 1–19, 2009.
[21]C.Y. Tsai, and S.H. Chung, A personalized route recommendation service for theme parks using RFID information and tourist behavior, Decision Support Systems, Vol. 52, No. 2, pages 514–527, 2012.
[22]W. Wang, H. Yin, L. Chen, Y. Sun, S. Sadiq, and X. Zhou, Geo-SAGE: A geographical sparse additive generative model for spatial item recommendation, Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 1255–1264, 2015.
[23]L.Y. Wei, Y. Zheng, and W.C. Peng, Constructing popular routes from uncertain trajectories, Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 195–203, 2012.
[24]H. Zhang, M. Korayem, D. J. Crandall, and G. Lebuhn, Mining photo-sharing websites to study ecological phenomena, Proceedings of the 21st International Conference on World Wide Web, pages 749–758, 2012.
[25]C. Zhang, H. Liang, K. Wang, and J. Sun, Personalized trip recommendation with POI availability and uncertain traveling time, Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pages 911–920, 2015.
[26]V. W. Zheng, Y. Zheng, X. Xie, and Q. Yang, Collaborative location and activity recommendations with GPS history data, Proceedings of the 19th International Conference on World Wide Web, pages 1029–1038, 2010.