臺灣博碩士論文加值系統

此篇論文中提出一個嶄新的旅遊行程推薦方法，其運用公眾傾向和社群影響來分析使用者對特定景點的喜好傾向，將少量的喜好景點透過景點關連性擴充景點清單後尋找出最佳旅遊行程路徑。不同於傳統基於歷史資訊或是協同過濾等推薦方法，藉由網路上異質性的資料來源進行大量資訊收集，建立針對特定物件的大眾喜好傾向機率模型，應用在基於使用者特徵的喜好傾向分類。另外，我們以使用者為中心建構社群影響向量來表示使用者與社群成員之間的喜好傾向影響力，根據不同的社群網路平台所提供的互動模式，評估社群成員之間的影響程度形成喜好傾向影響力。除此之外，透過網路針對特定景點收集大量相關文章，分析特定景點與其他景點關聯程度，結合大眾喜好相似度與景點距離建構景點關聯圖。此篇論文的目的是利用大眾喜好推估個別使用者喜好傾向，再進一步考慮使用者社群中鄰居對他的喜好傾向影響力進行喜好機率調整，挑選出喜好的景點以景點關聯圖來擴充景點多樣性，考慮景點之環境條件後，建構具時窗之使用者-社群-景點圖用一啟發演算法找出旅遊行程路徑。

The purposed in this thesis is to develop a novel associative journey scheduling method which employs public preference and social influence to classify user preference and uses point of interest (POI) relationship to extend preference list for journey scheduling. Unlike traditional content-based or collaborative filtering recommendation approaches, we collected large scale information from heterogeneous data sources to construct the public preference model for user’s feature-based preference orientation classification. Moreover, the social influence vector of target user is constructed to analyze social influence of preference between users in it. According to the different online social networks, corresponding types of interaction are adopted to estimate the degree of social influence between users. In addition, we use a large number of articles about specific POI to analyze association degree between POIs with public preferences similarity and distance and construct POI related graph.
The purpose method deals with the recommended list that contains few items. There two main advantages of the proposed method: 1. Any type of recommendation system can be applied in the proposed method；2. It can find out some POIs not in recommend list. In our experiment, the information sources (includes: blogs, news and online social networks) construct public preference model. Moreover, Facebook, the most famous social media, is the platform selected for social relationship analysis. The experimental result shows our approach innovation and practicable.

摘 要 III
Abstract IV
誌 謝 VI
Contents VII
List of Tables VIII
List of Figures IX
Chapter 1 Introduction 1
1.1 Motivation 3
1.2 Issues and Challenges 6
1.3 Contribution 8
1.4 Organization 9
Chapter 2 Related Works 10
2.1 Travel Recommendation System 10
2.2 Journey Scheduling Problem 13
2.3 Online Social Network 14
Chapter 3 Problem Statement 15
Chapter 4 An Associative Journey Scheduling Method 17
4.1 Heterogeneous Data Collection 20
4.2 Public Preference Model Generation 23
4.2.1 Data Source Importance Analysis 23
4.2.2 Heterogeneous Data Source Feature Integration 24
4.3 Suitable POIs Selection 25
4.3.1 Public Preference Score Calculation 25
4.3.2 Social Influence Adjustment 28
4.4 Journey Scheduling Solution 30
4.4.1 Related POI Graph Construction 30
4.4.2 User-Social-POI Graph with Time Window Construction 30
4.4.3 Heuristic Algorithm for USPTW Graph. 31
Chapter 5 Experiments and Discussion 34
5.1 Procedure and Design 34
5.2 Data Set 36
5.3 Experiment Results and Analysis 38
Chapter 6 Conclusion and Future Work 42
References 44
Appendix A 48

[1]UNWTO, http://www2.unwto.org/
[2]Tourism Bureau, M.O.T.C., Republic of China. “2013 Survey of Travel by R.O.C. Citizens.
[3]Eric Hsueh-Chan Lu, Ching-Yu Chen and Vincent S. Tseng. “Personalized trip recommendation with multiple constraints by mining user check-in behaviors, Proceedings of the 20th International Conference on Advances in Geographic Information Systems, pp. 209-218, 2012.
[4]Y. Huang and L. Bian, “A Bayesian Network and Analytic Hierarchy Process Based Personalized Recommendations for Tourist Attractions over the Internet, Expert Systems with Applications, 36(1), pp. 933-943, 2009.
[5]C.-S. Lee, Y.-C. Chang and M.-H. Wang, “Ontological Recommendation Multi-Agent for Tainan City Travel, Expert Systems with Applications, 36(3), pp. 6740-6753, 2009.
[6]M. Clements, P. Serdyukov, A. P. de Vries and M. J.T. Reinders, “Personalized Travel Recommendation based on Location Co-occurrence, CoRR, abs/1106.5213, 2011.
[7]T. Horozov, N. Narasimhan and V. Vasudevan, “Using Location for Personalized POI Recommendations in Mobile Environments, in SAINT, pp. 124-129, 2006.
[8]Adomavicius, G. and Tuzhilin, A. “Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions, IEEE Transactions on Knowledge and Data Engineering, Volume: 17, Issue: 6, pp. 734-749, 2005.
[9]Diaby, M., Viennet, E. and Launay, T. “Toward the next generation of recruitment tools: An online social network-based job recommender system, 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 821-828, 2013.
[10]Bedi, P. and Agarwal, S.K. “Preference Learning in Aspect-Oriented Recommender System, International Conference on Computational Intelligence and Communication Networks (CICN), pp. 611-615, 2011.
[11]M. Ye, P. Yin and W.-C. Lee, “Location Recommendation for Location-Based Social Networks, in ACM GIS, pp. 458-461, 2010.
[12]Ghazanfar, M.A. and Prugel-Bennett, A. “A Scalable, Accurate Hybrid Recommender System, Third International Conference on Knowledge Discovery and Data Mining (WKDD), pp. 94-98, 2010.
[13]J. Delgado and N. Ishii, “Memory-Based Weighted-Majority Prediction for Recommender Systems, Proc. ACM SIGIR Workshop Recommender Systems: Algorithms and Evaluation, 1999.
[14]T. Hofmann, “Collaborative Filtering via Gaussian Probabilistic Latent Semantic Analysis, Proc. 26th Ann. Int’l ACM SIGIR Conf., pp.259-266, 2003.
[15]B. Marlin, “Modeling User Rating Profiles for Collaborative Filtering, Proc. 17th Ann. Conf. Neural Information Processing Systems (NIPS), 2003.
[16]D. Pavlov and D. Pennock, “A Maximum Entropy Approach to Collaborative Filtering in Dynamic, Sparse, High-Dimensional Domains, Proc. 16th Ann. Conf. Neural Information Processing Systems (NIPS), 2002.
[17]X. Lu, C. Wang, J.-M. Yang, Y. Pang and L. Zhang, “Photo2Trip: Generating Travel Routes from Geo-Tagged Photos for Trip Planning, in ACM MM, pp. 143-152, 2010.
[18]Y. Zheng and X. Xie, “Learning Travel Recommendations from User-Generated GPS Traces, ACM Trans. on Intelligent Systems and Technologies, v.2 n.1, p.1-29, 2011.
[19]C. Zhou and X. Meng, “STS Complex Spatio-Temporal Sequence Mining in Flickr, In DASFAA, pp. 208-223, 2011.
[20]M. Xie, L. V.S. Lakshmanan and P. T. Wood, Breaking out of the Box of Recommendations: From Items to Packages, in ACM RecSys, pp.151–158, 2010.
[21]Y. Ge, Q. Liu, H. Xiong, A. Tuzhilin and J. Chen, Cost-Aware Travel Tour Recommendation, in KDD, pp. 983-991, 2011.
[22]Q. Liu, Y. Ge, Z. Li, E. Chen and H. Xiong, Personalized Travel Package Recommendation, in ICDM, pp. 407-416, 2011.
[23]Kimberlee Morrison, “The Growth of Social Media: From Passing Trend to International Obsession, http://socialtimes.com/, 2014.
[24]Meng-Hsuan Fu, Ling-Yu Chen, Kuan-Rong Lee and Yaw-Huang Kuo, “A Novel Opinion Analysis Scheme Using Social Relationships on Microblog, Springer Netherlands, Future Information Technology, Application, and Service, Volume 1, pp.687-695, 2012.
[25]B.L. Golden, L. Levy, and R. Vohra. The orienteering problem. Naval Research, Logistics, 34:307-318, 1987.
[26]Chao, I.-M., B. L. Golden, E. A. Wasil. 1996b. The team orienteering problem, Eur. J. Oper. Res. 88(3) 464–474.
[27]Kantor, M. G., M. B. Rosenwein. 1992. The orienteering problem with time windows. J. Oper. Res. Soc. 43(6) 629–635.
[28]P. Vansteenwegen, D. Van Oudheusden. The mobile tourist guide: an OR opportunity. OR Insights 2007; 20(3):21-7.