目前人們時常遇到一個問題，經常在某個地點活動結束過後，因為事前未詳細規劃或者可活動地點眾多而導致不知道該選擇何處或何種活動做為下一步行程。所以，若是我們能提出有效的方法幫助使用者找到符合自己本身的地點及活動需求，那麼將是一個有用的創新應用，例如使用者剛在電影院看完電影後，我們推薦他接下來可以去保齡球館打保齡球。
本研究針對使用者當下最新的打卡資訊作分析，並找出使用者下一步的地點及活動需求，本研究提出連續行程媒合模型，利用時間、地點、人物以及活動各種特徵為基礎的分析模型，找出跟使用者當下狀態最相似的連續行程，然後推薦給使用者下一步的地點及該地點可進行的活動。我們嘗試收集大量部落格文章及過往打卡資訊，擷取使用者個人資訊、去過的地點、所進行的活動…等等，然後利用這些資料訓練出連續行程。
　　我們提出了擷取活動及地點的方法，擷取活動有著不錯的效果，但是擷取地點的正確率偏低而錯誤的地點會降低系統的效能。我們的模型在只使用先前的打卡資訊當作資料來源時，效能較為優異，但只使用部落格文章時則略差。而我們提出的CIMM的top-1 inclusion rate約為30%，表示我們提出的CIMM能在一定的準確度之下推薦使用者接下來的地點及活動。

Many people often encounter a problem that they haven’t made detailed itinerary before a journey, and then they don’t know where or what kind of activity is suitable as the next location and activity after the end of an event or an activity in a place. We intend to propose an effective method to help users find next locations and activities in line with their needs. To our knowledge, this is an innovative and useful technique. For example, users just after watching the film in the cinema, we recommended that they can go to the bowling alley play bowling ball next.
In this study, we analyze user’s current check-in data and find out the next location and activity needs based on their current status. We propose the Consecutive Itinerary Matching Model. This model uses time, location, people, and activity as features to find the most similar “Consecutive Itinerary” associated with user’s current status, and then recommend users next locations and activities. We collected a large number of blog articles and check-in data, and we retrieved user's personal information, visited places, participated activities, etc., and then used these data to train consecutive itineraries. Based on the trained consecutive itineraries, we can effectively recommend user-expected locations and activities associated with these locations.
We proposed the method of location and activity extraction. The method of activity extraction is effective, but the precision of location extraction is only 65.3%, and the incorrect location will affect the performance of our model. The top-n inclusion rate of our model only using previous check-in data as data resource is better than only using blog articles. Our approach achieved about 30% top-1 inclusion rate, this means our model can recommend user’s next location and activity under certain precision.

[1] A. Nisgav, and B. Patt-Shamir, “Finding similar users in social networks: extended abstract.” 21st Annual ACM Symposium on Parallel Algorithms and Architectures, pp. 169–177, Calgary, Alberta, Canada, Aug 2009.
[2] A. Monreale, F. Pinelli, R. Trasarti and F. Giannotti, “WhereNext: a Location Predictor on Trajectory Pattern Mining,” KDD’09, Paris, France, Jul 2009.
[3] B. Berjani and T. Strufe, “A Recommendation System for Spots in Location-Based Online Social Networks,” SNS’11, Salzburg, Austria, Apr 2011.
[4] B. Jiang, J. Yin, and S. Zhao, “Characterizing the human mobility pattern in a large street network,” Physical Review E, 80(2):021136, Aug. 2009.
[5] C. Elkan, “Log-linear models and conditional random fields,” CIKM, 2008.
[6] E. J. Cho, S. A. Myers and J. Leskovec, “Friendship and Mobility: User Movement in Location-Based Social Networks,” KDD’11, San Diego, CA, USA, Aug 2011.
[7] G. L. Chen and F. Rahman, “Analyzing privacy designs of mobile social networking applications,” In Proceedings of the IEEE/IFIP International Symposium on Trust, Security and Privacy for Pervasive Applications (TSP), pages 83–88, Shanghai, China, Dec 2008.
[8] H. Yang, B. Yang, X. Zhou, C. Zhou, Z. Wang and Z. Chai, “Community discovery and sentiment mining for Chinese BLOG,” In Proc. of FSKD’10, pp.1740-1745, Yantai, China, Aug 2010.
[9] I. Guy, I. Ronen, and E. Wilcox, “Do you know?: recommending people to invite into your social network,” International Conference on Intelligent User Interfaces, pp. 77–86, Sanibel Island, Florida, USA, Feb 2009.
[10] J. Goldenberg and M. Levy, “Distance is not dead: Social interaction and geographical distance in the internet era,” Arxiv, abs/0906.3202, 2009.
[11] K. C. Park, Y. J. Jeong and S. H. Myaeng, “Detecting Experiences from Weblogs,” In Proc. of the ACL’10, pp.1464-1472, Uppsala, Sweden, Jul 2010.
[12] K. El-Arini, G. Veda, D. Shahaf, and C. Guestrin, “Turning down the noise in the blogosphere,” In Proc. of KDD’09, Paris, France, Jul 2009.
[13] L. Y. Wei and W. C. Peng, “Trajectory Pattern Mining in Social Media,” Master thesis, Univ. of Chiao Tung, Taiwan, 2012.
[14] M. J. Lee and C. W. Chung, “A User Similarity Calculation Based on the Location for Social Network Services,” DASFAA’11, Hong Kong, China, Apr 2011.
[15] M. Ye, P. F. Yin and W. C. Lee, “Location Recommendation for Location-based Social Networks,” ACM GIS’10, San Jose, CA, USA, Nov 2010.
[16] M. Morzy, “Mining Frequent Trajectories of Moving Objects for Location Prediction,” MLDM’07, Leipzig, Germany, Jul 2007.
[17] M. Morzy, “Prediction of Moving Object Location Based on Frequent Trajectories,” ISCIS’06, Istanbul, Turkey, Nov 2006.
[18] M. C. Gonzalez, C. A. Hidalgo, and A.-L. Barabasi, “Understanding individual human mobility patterns,” Nature, 453(7196):779–782, 2008.
[19] N. Li and G. L. Chen, “Analysis of a Location-based Social Network,” International Conference on Computational Science and Engineering, IEEE’09, Vancouver, BC, Canada, Aug 2009.
[20] N. Eagle and A. Pentland, “Eigenbehaviors: Identifying structure in routine,” Behavioral Ecology and Soc., 2009.
[21] P. Kotler, “Marketing management: Analysis, planning, implementation, and control,” (9th ed.), NJ.: Prentice-Hall,1997.
[22] Q. N. Li, Y. Zheng, X. Xie, Y. K. Chen, W. Y. Liu and W. Y. Ma, “Mining User Similarity Based on Location History,” ACM GIS'08, Irvine, California, USA, Nov 2008.
[23] S. H. Yang, B. Long, A. Smola, N. Sadagopan, Z. H. Zheng and H. Y. Zha, “Like like alike — Joint Friendship and Interest Propagation in Social Networks,” WWW’11, Hyderabad, India, Mar 2011.
[24] Social networking and craigslist top mobile destinations, says openwave. Reporter Wireless and Mobile News, Mar 2009.
[25] X. C. Ni, G. R. Xue, X. Ling, Y. Yu and Q. Yang, “Exploring in the Weblog Space by Detecting Informative and Affective Articles,” In Proc. of WWW’07, pp.281-290, Banff, Alberta, May 2007.
[26] Y. Zheng, L. Z. Zhang, X. Xie and W. Y. Ma, “Mining Interesting Locations and Travel Sequences from GPS Trajectories,” WWW’09, Madrid, Spain, Apr 2009.
[27] Y. Lee, H. Y. Jung, W. S. Song and J. H. Lee, “Mining the Blogosphere for Top News Stories Identification,” In Proc. of SIGIR’10, pp.395-402, UniMail, Geneva, Switzerland, Jul 2010.
[28] Z. Li, B. Ding, J. Han, R. Kays, and P. Nye, “Mining periodic behaviors for moving objects,” KDD’10, Washington, DC, USA, Jul 2010.
[29] 82 million location-based mobile social networking subscriptions by 2013. ABI Research Market Analysis Report, Nov 2008.
[30] 王維誠, “風景區觀光吸引力、服務品質與滿意度之研究─以阿里山國家風景區為例,” Master thesis, Univ. of Nan Hua, Taiwan. 2009.
[31] 林晏州, “遊憩者選擇遊憩區行為之研究,” 都市與計畫, no. 10, pp.33-49, 1984.