學術產出-Theses

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

  • No doi shows Citation Infomation
題名 利用維基百科及網路相簿從遊記探勘個人化旅遊行程
Mining personalized trip plan from travelogues using wikipedia and web albums
作者 吳容瑜
貢獻者 沈錳坤
Shan, Man Kwan
吳容瑜
關鍵詞 工作流程
日期 2010
上傳時間 29-Sep-2011 18:25:09 (UTC+8)
摘要 近幾年國內的自助旅遊風氣逐漸盛行,行前準備對一般人而言必須花費不少時間。我們必須從網路上收集各方資料加以整理,再規劃出理想的行程,所以行程規劃非常耗時。因此,本篇論文研究由網友撰寫的旅遊文章中,利用維基百科和網路相簿作為輔助工具,探勘分析旅遊景點與路線,並根據使用者的需求提供個人化的行程安排,以作為行程規劃之參考。
     我們先將遊記標題透過中文斷詞系統進行斷詞,再利用維基百科確認是否為景點名稱。接著我們利用遊記作者權威性與景點重要性之間的相互強化關係來判斷每個景點的重要性。取得景點名稱及其重要性之後,我們利用遊記的文章結構與特性進而判斷遊記中的旅遊路線,由此步驟可得知景點在旅遊路線中的前後關係。此外,我們利用網路相簿中旅遊相片的資訊預估景點停留時間,並且從交通查詢網站取得景點間的交通時間。
     系統根據使用者給定的必經景點,推薦使用者符合條件的旅遊路線。接著,根據使用者選定的旅遊路線,考量使用者給定的時間限制、景點開放時間的限制與景點交通時間的限制,排定行程內各景點適合的參訪時間。最後,根據上述步驟的結果,系統便可推薦使用者個人化的行程。
     我們以國內知名BBS批踢踢實業坊上的日本旅遊看版內之遊記作為實驗資料來源,並參考維基百科及Flickr網路相簿,實作出個人化的旅遊行程推薦系統。實驗顯示本論文所萃取出的景點名稱,其精確度92%、召回率100%,而景點停留時間與Ground Truth的誤差範圍為3.16%。最後,滿意度評估顯示本論文的推薦系統符合個人化需求。
Trip planning is an important and time-consuming step for backpackers. Most research focuses on finding the travel sequence from different data sources such as blog, photos and GPS. Although these approaches can recommend some popular travel sequences for a tourist, but tourist’s place preferences and temporal constraints are not considered. In this thesis, we propose an approach for personalized trip planning which takes tourist’s preference and temporal constraint into consideration.
     In the proposed approach, first the place names are extracted from travelogues with the aid of the Wikipedia. Then the travel sequences are extracted from travelogues. Based on the relationship of mutual reinforcement between the authority of a place and the hub of a travelogue author, the authority of each place is derived. Moreover, the stay time of each place is estimated from the information of travel photos of a web album. Finally, based on the user specified place preference and temporal constraints, this thesis presents the algorithms to arrange a personalized trip for a user. The experiments show that the place name extraction achieves 92% precision and 100% recall. For the estimation of place stay time, the error is 3.16% compared with the ground truth collected from well-known backpacker site.
參考文獻 [1] Y. Arase, X. Xie, T. Hara, S. Nishio, “Mining People’s Trips from Large Scale Geo-tagged Photos,” Proc. of the 18th ACM International Conference on Multimedia MM, 2010.
[2] C. Bettini, X.S. Wang, S. Jajodia, “Temporal Reasoning in Workflow Systems,” Journal of Distributed and Parallel Database, Vol. 11, Issue 3, 2002.
[3] M. D. Choudhury, M. Feldman, S. A. Yahia, N. Golbandi, R. Lempel, and C. Yu, “Constructing Travel Itineraries from Tagged Geo-Temporal Breadcrumbs,” Proc. of the 19th ACM International Conference on World Wide Web WWW, 2010.
[4] R. Dechter, I. Meiri, J. Pearl, “Temporal Constraint Networks,” Journal of Artificial Intelligence, Vol. 49, Issue 1-3, 1991.
[5] J. Eder, E. Panagos, and M. Rabinovich, “Time Constraints in Workflow System,” Proc. of the 11th International Conference on Advanced Information Systems Engineering CAiSE, 1999.
[6] F. Giannotti, M. Nanni, D. Pedreschi, and F. Pinelli, “Trajectory Pattern Mining,” Proc. of the 13th ACM International Conference on Knowledge Discovery and Data Mining KDD, 2007.
[7] A. Goyal, F. Bonchi, V.S. Lakshmanan, “Discovering Leaders from Community Actions,” Proc. of the 17th ACM Conference on Information and Knowledge Management CIKM, 2008.
[8] Q. Hao, R. Cai, J.M. Yang, R. Xiao, L. Liu, S. Wang, and L. Zhang, “TravelScope:Standing on the Shoulders of Dedicated Travelers,” Proc. of the 17th ACM International Conference on Multimedia MM, 2009.
[9] F. Jing, L. Zhang, and W.Y. Ma, “VirtualTour: An Online Travel Assistant Based on High Quality Images,” Proc. of the 14th ACM International Conference on Multimedia MM, 2006.
[10] R. Ji , X. Xie, H. Yao, and W.Y. Ma, “Mining City Landmarks from Blogs by Graph Modeling,” Proc. of the 17th ACM International Conference on Multimedia MM, 2009.
[11] L. Kennedy, and M. Naaman, “Generating Diverse and Representative Image Search Results for Landmarks,” Proc. of the 17th ACM International Conference on World Wide Web WWW, 2008.
[12] H. Kori, S. Hattori, T. Tezuka, and K. Tanaka, “Automatic Generation of Multimedia Tour Guide from Local Blogs,” Multimedia Modeling MMM 2007, LNCS 4351 pp. 690–699.
[13] T. Kurashima, T. Tezuka, and K. Tanaka, “Mining and Visualizing Local Experiences from Blog Entries,” International Conference on Database and Expert Systems Applications DEXA 2006, LNCS 4080, pp. 213-222.
[14] J.Q. Lin, Y.S. Fan, M.C. Zhou, “Timing Constraints Workflow Nets for Workflow Analysis,” IEEE Trans. on System, Man, and Cybernetics, Vol. 33, Issue 2, 2003, pp. 179-193.
[15] X. Lu, C.H. Wang, J.M. Yang, Y.W. Pang, L. Zhang “Photo2Trip : Generating Travel Routes from Geo-Tagged Photos for Trip Planning,” Proc. of the 18th ACM International Conference on Multimedia MM, 2010.
[16] A. Popescu, G. Grefenstette, “Deducing Trip Related Information from Flickr,” Proc. of the 18th ACM International Conference on World Wide Web WWW, 2009.
[17] A. Popescu, G. Grefenstette, and H. Bouamor, “Mining a Multilingual Geographical Gazetteer from the Web,” Proc. of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, pp.58-65, September 15-18, 2009.
[18] A. Popescu, G. Grefenstette, and P. A. Moëllic, “Gazetiki: Automatic Creation of a Geographical Gazetteer,” Proc. of the 8th ACM/IEEE-CS Joint Conference on Digital Libraries JCDL, 2008.
[19] A. Popescu, G. Grefenstette, and P. A. Moëllic, “Mining Tourist Information from User-supplied Collections,” Proc. of the 18th ACM International Conference on Information and Knowledge Management CIKM, 2009.
[20] J. Pei, J.W. Han, B. Mortazavi-Asl, H. Pinto, Q.M. Chen, U. Dayal, and M. C. Hsu, “PrefixSpan: Mining Sequential Patterns Efficiently by Prefix-Projected Pattern Growth,” Proc. of the 17th ACM International Conference on Data Engineering ICDE, 2001.
[21] F. A. Twaroch, P. D. Smart, and C. B. Jones, “Mining the Web to Detect Place Names,” Proc. of the 2nd International Workshop on Geographic Information Retrieval GIR, 2008.
[22] X. Wu, J.T. Li, Y.D. Zhang, S. Tang, and S.Y. Neo, “Personalized Multimedia Web Summarizer for Tourist,” Proc. of the 17th ACM International Conference on World Wide Web WWW, 2008.
[23] Y. Zheng, L.Z. Zhang, X. Xie, W.Y. Ma, "Mining Interesting Locations and Travel Sequences from GPS Trajectories," Proc. of the 18th ACM International Conference on World Wide Web WWW, 2009.
[24] Y. T. Zheng, M. Zhao, Y. Song, H. Adam, U. Buddemeier, A. Bissacco, F. Brucher, T.S. Chua1, H. Neven, and J. Yagnik, “Tour the World:a Technical Demonstration of a Web-Scale Landmark Recognition Engine,” Proc. of the 17th ACM International Conference on Multimedia MM, 2009.
[25] 林信男, 維護工作流程時間限制一致性之研究, 國立中山大學資訊管理學系研究所碩士論文, 2000.
描述 碩士
國立政治大學
資訊科學學系
97753037
99
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0097753037
資料類型 thesis
dc.contributor.advisor 沈錳坤zh_TW
dc.contributor.advisor Shan, Man Kwanen_US
dc.contributor.author (Authors) 吳容瑜zh_TW
dc.creator (作者) 吳容瑜zh_TW
dc.date (日期) 2010en_US
dc.date.accessioned 29-Sep-2011 18:25:09 (UTC+8)-
dc.date.available 29-Sep-2011 18:25:09 (UTC+8)-
dc.date.issued (上傳時間) 29-Sep-2011 18:25:09 (UTC+8)-
dc.identifier (Other Identifiers) G0097753037en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/50992-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學學系zh_TW
dc.description (描述) 97753037zh_TW
dc.description (描述) 99zh_TW
dc.description.abstract (摘要) 近幾年國內的自助旅遊風氣逐漸盛行,行前準備對一般人而言必須花費不少時間。我們必須從網路上收集各方資料加以整理,再規劃出理想的行程,所以行程規劃非常耗時。因此,本篇論文研究由網友撰寫的旅遊文章中,利用維基百科和網路相簿作為輔助工具,探勘分析旅遊景點與路線,並根據使用者的需求提供個人化的行程安排,以作為行程規劃之參考。
     我們先將遊記標題透過中文斷詞系統進行斷詞,再利用維基百科確認是否為景點名稱。接著我們利用遊記作者權威性與景點重要性之間的相互強化關係來判斷每個景點的重要性。取得景點名稱及其重要性之後,我們利用遊記的文章結構與特性進而判斷遊記中的旅遊路線,由此步驟可得知景點在旅遊路線中的前後關係。此外,我們利用網路相簿中旅遊相片的資訊預估景點停留時間,並且從交通查詢網站取得景點間的交通時間。
     系統根據使用者給定的必經景點,推薦使用者符合條件的旅遊路線。接著,根據使用者選定的旅遊路線,考量使用者給定的時間限制、景點開放時間的限制與景點交通時間的限制,排定行程內各景點適合的參訪時間。最後,根據上述步驟的結果,系統便可推薦使用者個人化的行程。
     我們以國內知名BBS批踢踢實業坊上的日本旅遊看版內之遊記作為實驗資料來源,並參考維基百科及Flickr網路相簿,實作出個人化的旅遊行程推薦系統。實驗顯示本論文所萃取出的景點名稱,其精確度92%、召回率100%,而景點停留時間與Ground Truth的誤差範圍為3.16%。最後,滿意度評估顯示本論文的推薦系統符合個人化需求。
zh_TW
dc.description.abstract (摘要) Trip planning is an important and time-consuming step for backpackers. Most research focuses on finding the travel sequence from different data sources such as blog, photos and GPS. Although these approaches can recommend some popular travel sequences for a tourist, but tourist’s place preferences and temporal constraints are not considered. In this thesis, we propose an approach for personalized trip planning which takes tourist’s preference and temporal constraint into consideration.
     In the proposed approach, first the place names are extracted from travelogues with the aid of the Wikipedia. Then the travel sequences are extracted from travelogues. Based on the relationship of mutual reinforcement between the authority of a place and the hub of a travelogue author, the authority of each place is derived. Moreover, the stay time of each place is estimated from the information of travel photos of a web album. Finally, based on the user specified place preference and temporal constraints, this thesis presents the algorithms to arrange a personalized trip for a user. The experiments show that the place name extraction achieves 92% precision and 100% recall. For the estimation of place stay time, the error is 3.16% compared with the ground truth collected from well-known backpacker site.
en_US
dc.description.tableofcontents 表目錄 vii
     圖目錄 viii
     第一章 前言 1
     1.1動機 1
     1.2論文架構 3
     第二章 相關研究 4
     2.1由部落格探勘行程 4
     2.2由網路相簿探勘行程 7
     2.3由GPS軌跡資料探勘行程 8
     第三章 研究方法與步驟 12
     3.1系統架構 12
     3.2景點名稱萃取 14
     3.2.1遊記文章特性 14
     3.2.2利用維基百科取得景點名稱 15
     3.3遊記路線之萃取 19
     3.4景點之重要性分析 22
     3.5預估景點停留時間 25
     3.6個人化路徑之產生 28
     3.7時間一致性檢查 32
     3.8 行程時間推論 38
     第四章 系統實作與實驗評估 42
     4.1系統實作 42
     4.2實驗評估 47
     4.2.1評估景點名稱準確率 47
     4.2.2評估停留時間 49
     4.2.3系統推薦行程之滿意程度評估 50
     第五章 結論與未來研究 52
     參考文獻 53
zh_TW
dc.language.iso en_US-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0097753037en_US
dc.subject (關鍵詞) 工作流程zh_TW
dc.title (題名) 利用維基百科及網路相簿從遊記探勘個人化旅遊行程zh_TW
dc.title (題名) Mining personalized trip plan from travelogues using wikipedia and web albumsen_US
dc.type (資料類型) thesisen
dc.relation.reference (參考文獻) [1] Y. Arase, X. Xie, T. Hara, S. Nishio, “Mining People’s Trips from Large Scale Geo-tagged Photos,” Proc. of the 18th ACM International Conference on Multimedia MM, 2010.zh_TW
dc.relation.reference (參考文獻) [2] C. Bettini, X.S. Wang, S. Jajodia, “Temporal Reasoning in Workflow Systems,” Journal of Distributed and Parallel Database, Vol. 11, Issue 3, 2002.zh_TW
dc.relation.reference (參考文獻) [3] M. D. Choudhury, M. Feldman, S. A. Yahia, N. Golbandi, R. Lempel, and C. Yu, “Constructing Travel Itineraries from Tagged Geo-Temporal Breadcrumbs,” Proc. of the 19th ACM International Conference on World Wide Web WWW, 2010.zh_TW
dc.relation.reference (參考文獻) [4] R. Dechter, I. Meiri, J. Pearl, “Temporal Constraint Networks,” Journal of Artificial Intelligence, Vol. 49, Issue 1-3, 1991.zh_TW
dc.relation.reference (參考文獻) [5] J. Eder, E. Panagos, and M. Rabinovich, “Time Constraints in Workflow System,” Proc. of the 11th International Conference on Advanced Information Systems Engineering CAiSE, 1999.zh_TW
dc.relation.reference (參考文獻) [6] F. Giannotti, M. Nanni, D. Pedreschi, and F. Pinelli, “Trajectory Pattern Mining,” Proc. of the 13th ACM International Conference on Knowledge Discovery and Data Mining KDD, 2007.zh_TW
dc.relation.reference (參考文獻) [7] A. Goyal, F. Bonchi, V.S. Lakshmanan, “Discovering Leaders from Community Actions,” Proc. of the 17th ACM Conference on Information and Knowledge Management CIKM, 2008.zh_TW
dc.relation.reference (參考文獻) [8] Q. Hao, R. Cai, J.M. Yang, R. Xiao, L. Liu, S. Wang, and L. Zhang, “TravelScope:Standing on the Shoulders of Dedicated Travelers,” Proc. of the 17th ACM International Conference on Multimedia MM, 2009.zh_TW
dc.relation.reference (參考文獻) [9] F. Jing, L. Zhang, and W.Y. Ma, “VirtualTour: An Online Travel Assistant Based on High Quality Images,” Proc. of the 14th ACM International Conference on Multimedia MM, 2006.zh_TW
dc.relation.reference (參考文獻) [10] R. Ji , X. Xie, H. Yao, and W.Y. Ma, “Mining City Landmarks from Blogs by Graph Modeling,” Proc. of the 17th ACM International Conference on Multimedia MM, 2009.zh_TW
dc.relation.reference (參考文獻) [11] L. Kennedy, and M. Naaman, “Generating Diverse and Representative Image Search Results for Landmarks,” Proc. of the 17th ACM International Conference on World Wide Web WWW, 2008.zh_TW
dc.relation.reference (參考文獻) [12] H. Kori, S. Hattori, T. Tezuka, and K. Tanaka, “Automatic Generation of Multimedia Tour Guide from Local Blogs,” Multimedia Modeling MMM 2007, LNCS 4351 pp. 690–699.zh_TW
dc.relation.reference (參考文獻) [13] T. Kurashima, T. Tezuka, and K. Tanaka, “Mining and Visualizing Local Experiences from Blog Entries,” International Conference on Database and Expert Systems Applications DEXA 2006, LNCS 4080, pp. 213-222.zh_TW
dc.relation.reference (參考文獻) [14] J.Q. Lin, Y.S. Fan, M.C. Zhou, “Timing Constraints Workflow Nets for Workflow Analysis,” IEEE Trans. on System, Man, and Cybernetics, Vol. 33, Issue 2, 2003, pp. 179-193.zh_TW
dc.relation.reference (參考文獻) [15] X. Lu, C.H. Wang, J.M. Yang, Y.W. Pang, L. Zhang “Photo2Trip : Generating Travel Routes from Geo-Tagged Photos for Trip Planning,” Proc. of the 18th ACM International Conference on Multimedia MM, 2010.zh_TW
dc.relation.reference (參考文獻) [16] A. Popescu, G. Grefenstette, “Deducing Trip Related Information from Flickr,” Proc. of the 18th ACM International Conference on World Wide Web WWW, 2009.zh_TW
dc.relation.reference (參考文獻) [17] A. Popescu, G. Grefenstette, and H. Bouamor, “Mining a Multilingual Geographical Gazetteer from the Web,” Proc. of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, pp.58-65, September 15-18, 2009.zh_TW
dc.relation.reference (參考文獻) [18] A. Popescu, G. Grefenstette, and P. A. Moëllic, “Gazetiki: Automatic Creation of a Geographical Gazetteer,” Proc. of the 8th ACM/IEEE-CS Joint Conference on Digital Libraries JCDL, 2008.zh_TW
dc.relation.reference (參考文獻) [19] A. Popescu, G. Grefenstette, and P. A. Moëllic, “Mining Tourist Information from User-supplied Collections,” Proc. of the 18th ACM International Conference on Information and Knowledge Management CIKM, 2009.zh_TW
dc.relation.reference (參考文獻) [20] J. Pei, J.W. Han, B. Mortazavi-Asl, H. Pinto, Q.M. Chen, U. Dayal, and M. C. Hsu, “PrefixSpan: Mining Sequential Patterns Efficiently by Prefix-Projected Pattern Growth,” Proc. of the 17th ACM International Conference on Data Engineering ICDE, 2001.zh_TW
dc.relation.reference (參考文獻) [21] F. A. Twaroch, P. D. Smart, and C. B. Jones, “Mining the Web to Detect Place Names,” Proc. of the 2nd International Workshop on Geographic Information Retrieval GIR, 2008.zh_TW
dc.relation.reference (參考文獻) [22] X. Wu, J.T. Li, Y.D. Zhang, S. Tang, and S.Y. Neo, “Personalized Multimedia Web Summarizer for Tourist,” Proc. of the 17th ACM International Conference on World Wide Web WWW, 2008.zh_TW
dc.relation.reference (參考文獻) [23] Y. Zheng, L.Z. Zhang, X. Xie, W.Y. Ma, "Mining Interesting Locations and Travel Sequences from GPS Trajectories," Proc. of the 18th ACM International Conference on World Wide Web WWW, 2009.zh_TW
dc.relation.reference (參考文獻) [24] Y. T. Zheng, M. Zhao, Y. Song, H. Adam, U. Buddemeier, A. Bissacco, F. Brucher, T.S. Chua1, H. Neven, and J. Yagnik, “Tour the World:a Technical Demonstration of a Web-Scale Landmark Recognition Engine,” Proc. of the 17th ACM International Conference on Multimedia MM, 2009.zh_TW
dc.relation.reference (參考文獻) [25] 林信男, 維護工作流程時間限制一致性之研究, 國立中山大學資訊管理學系研究所碩士論文, 2000.zh_TW