臺灣博碩士論文加值系統

近年來,最受歡迎的推薦系統莫過於基於社群網路的個人化景點推薦系統,因為這類的系統會利用使用者自願在社群網路上留下的個人資訊,及個人的生活經驗及軌跡,推薦使用者可能喜愛的旅遊景點.如此便能省去行前進行旅遊規劃的時間,然而我們發現這類的服務往往都是針對個人去做推薦,而這個狀況並不符合大多數人的旅遊情況,因為旅遊時通常會與多人一起參加,鮮少單獨前往,像是和家人一起去野餐,或是和朋友一起去看電影.再者近年來目前各大的社群網站(Facebook、Meetup、Foursquare),在記錄打卡資料的同時也紀錄一同出遊的成員已成為一種趨勢.因此,本論文提出了HMUR( Hybrid Method with Users Rating)演算法,針對一群共同出遊的使用者(團體),進行旅遊景點的推薦.這個方法透過分析團體打卡資料及成員的個人資訊,以及根據使用者的評分來調整其推薦結果.最後,實驗部分則證明了我們所提出演算法能有效地進行團體推薦.

In recent years, the most popular recommender systems are none other than the personalized tourist attraction recommender systems on social networks, which use the personal profiles willingly provided by users on the social network and then recommend tourist attractions that the users may like based on their life experiences and trajectories. With such recommender systems, users can save time used to plan their travels ahead of time. We have found that most of these services focus on the individual when making recommendations. However, most people have company when they travel and are not alone. e.g., going picnics with family and watching movies with friends. Furthermore, looking at existing social websites (i.e. Facebook、Meetup、Foursquare), it has become a trend for check-in data to also include the accompanying members. This motivates the studies on group recommendation, which aims to recommend tourist attractions for a group of users. In this paper, we propose an algorithm named HMUR (Hybrid Method with Users Rating) to analyze the group information and user ratings, and make group recommendations. We conduct an experiments and the results show that the proposed algorithm is effective in making group recommendations, and outperforms baseline methods significantly.

Chinese Abstract i
Abstract ii
Acknowledgements iii
List of Contents iv
List of Figures v
List of Tables vi
Chapter 1 Introduction 1
Chapter 2 Related work 9
2.1 Recommender systems 9
2.1.1 Collaborative filtering recommender systems 9
2.1.2 Content-based recommender systems 10
2.1.3 Knowledge-based recommender systems 11
2.2 Group recommender systems 11
2.3 POI recommender systems 12
2.4 Technics related to our work 13
Chapter 3 Problem definition 14
Chapter 4 Algorithm 22
4.1 System framework 22
4.2 Offline processing 23
4.2.1 Analysis of group profiles 23
4.2.2 Clustering based on group check-in data 26
4.2.3 Adjustment of ratings 32
4.3 Online processing 35
4.3.1 Bit Similarity Checking (BSC) 35
4.3.2 Evaluation of POI scores 37
4.3.2.1 Calculation of similarity between two groups 38
4.3.2.1.1 Calculation of social-related similarity 38
4.3.2.1.2 Calculation of social POI-related similarity 40
4.3.2.2 Calculation of the POI scores 40
Chapter 5 Performance 42
5.1 Evaluation metrics 43
5.2 Setting an appropriate number of cluster 44
5.3 Comparison between k-means and k-kedoids clustering 45
5.3.1 Comparing the average number of categories 45
5.3.2 Comparing the query comparison of proportion between two methods 46
5.4 Baseline comparisons 47
5.5 Performance of algorithm with different relationship combinations 49
5.6 Analysis of group size 51
5.7 Influence of ratings 51
Chapter 6 Conclusions and future work 53
References 54

[1] Y. Arase, X. Xie, T. Hara, and S. Nishio, “Mining People’s Trips from Large Scale Geo-tagged Photos, Proceedings of the ACM Multimedia International Conference (ACM-MM), pp. 133-142, 2010.
[2] L. Baltrunas, T. Makcinskas, and F. Ricci, “Group recommendations with rank aggregation and collaborative filtering, Proceedings of the fourth ACM conference on Recommender systems, pp. 119-126, 2010.
[3] J. S. Breese, H. David, and K. Carl, “Empirical analysis of predictive algorithms for collaborative filtering, Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence. Morgan Kaufmann Publishers, pp. 43-52, 1998.
[4] A. J. Cheng, Y. Y Chen, Y. T. Huang, W. H. Hsu, and H. Y. M. Liao, “Personalized Travel Recommendation by Mining People Attributes from Community-Contributed Photos, Proceedings of the 19th ACM international conference on Multimedia. ACM, pp. 83-92, 2011.
[5] A. Crossen, J. Budzik, and K. J. Hammond, “Flytrap: intelligent group music recommendation, Proceedings of the 7th international conference on Intelligent user interfaces, pp. 184-185, 2002.
[6] T. R. Derrick, B. T. Bates, J. S. Dufek, “Evaluation of time-series data sets using the Pearson product-moment correlation coefficient, Medicine and Science in Sports and Exercise, pp. 919-928, 1994.
[7] M. Gartrell , X. Xing , Q. Lv, A. Beach, R. Han, S. Mishra, and K. Seada, “Enhancing Group Recommendation by Incorporating Social Relationship Interactions, Proceedings of the 16th ACM international conference on Supporting group work. ACM, pp. 97-106, 2010.
[8] T. Horozov, N. Narasimhan, and V. Vasudevan, “Using location for personalized POI recommendations in mobile, Int. Symposium on Applications and the Internet, pp. 1-6, 2006.
[9] 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. ACM, pp. 56-62, 2012.
[10] X. S. Khoshgoftaar, “A Survey of Collaborative Filtering Techniques, In Advances in Artificial Intelligence, vol. 19, no. 4, 2009.
[11] Y. Koren, R. Bell, and C.Volinsky, “Matrix factorization techniques for recommender systems, In Computer 42.8, pp. 30-37, 2009.
[12] J. J. Levandoski, M. Sarwat, A. Eldawy, and M. F. Mokbel, “LARS: A Location-Aware Recommender System, in Proc. IEEE 28th Int. Conf. Data Engineering, pp. 450-461, 2012.
[13] X. Li and T. Muarata, “Customizing knowledge-based recommender system by tracking analysis of user behavior, Proceeding on International Conference on Industrial Engineering and Engineering Management (IE＆EM), pp. 65-69, 2010.
[14] C. Luo, J.G. Lou, Q. Lin, Q. Fu, R. Ding, D. Zhang, Z. Wang, “Correlating events with time series for incident diagnosis, In 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 1583-1592, 2014.
[15] H. Ma, “On Measuring Social Friend Interest Similarities in Recommender Systems, Proceedings of the 37th international ACM SIGIR conference on Research ＆ development in information retrieval, ACM, pp. 465-474, 2014.
[16] J. F. McCarthy, “Pocket restaurant finder: A situated recommender systems for groups, In Proceeding of Workshop on Mobile Ad-Hoc Communication at the 2002 ACM Conference on Human Factors in Computer Systems, 2002.
[17] J. F. McCarthy, and T. D. Anagnost, “Musicfx: An arbiter of group preferences for computer supported collaborative workouts, Proceedings of the 1998 ACM conference on Computer supported cooperative work. ACM, pp.363-372, 1998.
[18] J. P. Michael, “A framework for collaborative, content-based and demographic filtering, Artificial Intelligence Review 13.5-6, pp. 393-408, 1999
[19] M. O’Connor, D. Cosley, J. A. Konstan, and J. Riedl. Polylens, “A recommender system for groups of user, European Conference on Computer-Supported Cooperative Work, pp. 199-218, 2001.
[20] S. Pizzutilo, B. D. Carolis, G. Cozzolongo, and F. Ambruoso, “Group modeling in a public space: methods, techniques, experiences, Proceedings of the 5th WSEAS International Conference on Applied Informatics and Communications, pp. 175-180, 2005.
[21] A. M. Rashid, G. Karypis, and J. Riedl. “Influence in ratings-based recommender systems: An algorithm-independent approach, Proc. of the SIAM International Conference on Data Mining. Pp. 556-560, 2005.
[22] J. Sang, T. Mei, J. T. Sun, C. Xu, and S. Li, “Probabilistic sequential POIs recommendation via check-in data, Proceedings of the 20th International Conference on Advances in Geographic Information Systems, ACM, pp. 402-405, 2012.
[23] M. Sarwat, J. J. Levandoski, A. Eldawy, and M. F. Mokbel, “LARS*: A Scalable and Efficient Location-Aware Recommender System, IEEE Transactions on Knowledge and Data Engineering TKDE, 2014.
[24] S. Seko, T. Yagi, M. Motegi, and S. Yo , Group recommendation using feature space representing behavioral tendency and power balance among members, Proceedings of the fifth ACM conference on Recommender systems, pp.101-108, 2011.
[25] S. B. Roy , S. Thirumuruganathan , S. A. Yahia , G. Das , and C. Yu, “Exploiting Group Recommendation Functions for Flexible Preferences, in 2014 IEEE 30th International Conference on Data Engineering. IEEE, pp. 412-423, 2014.
[26] D. Vanderkam, R. Schonberger, H. Rowley, S. Kumar, “Nearest Neighbor Search in Google Correlate, Google, 2013.
[27] H. Wang, T. Manolis, and M. Nikos, “Location recommendation in location-based social networks using user check-in data, Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM, pp,374-383, 2013.
[28] J. J. C. Ying, E. H. C. Lu, W. N. Kuo, and V. S. Tseng, “Urban point-of-interset recommendation by mining user check-in behaviors, Proceedings of the ACM SIGKDD International Workshop on Urban Computing, pp. 55-62, 2012.
[29] W. V. Zheng, et al, “Collaborative Filtering Meets Mobile Recommendation: A User-Centered Approach. Association for the Advancement of Artificial Intelligence, pp. 236-241, 2010.
[30] Z. Yu, X. Zhou, Y. Hao, and J. Gu, “Tv program recommendation for multiple viewers based on user profile merging, In User modeling and user-adapted interaction, pp. 63–82, 2006.
[31] “Amazon, http://www.amazon.com/.
[32] “Baidu, http://www.baidu.com/.
[33] “Foursquare, https://www. foursquare.com/.
[34] “Google, http://www.google.com/.
[35] “Netflix, http://www.netflix.com/.