研究生: |
王薏涵 Yi-Han Wang |
---|---|
論文名稱: |
基於用戶偏好興趣點類別的改良式興趣點推薦系統 An Improved Point of Interest Recommendation System Based on User Preferences on Interest Categories |
指導教授: |
徐俊傑
Chiun-Chieh Hsu |
口試委員: |
王有禮
Yue-Li Wang 林伯慎 Bor-Shen Lin |
學位類別: |
碩士 Master |
系所名稱: |
管理學院 - 資訊管理系 Department of Information Management |
論文出版年: | 2023 |
畢業學年度: | 111 |
語文別: | 中文 |
論文頁數: | 68 |
中文關鍵詞: | 興趣點 、基於位置的社交網路 、推薦系統 、基於內容的推薦方法 |
外文關鍵詞: | Point of Interest, Location-Based Social Network, Recommendation System, Content-Based Recommendation Method |
相關次數: | 點閱:203 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
隨著社交網路及行動設備的普及化,人們也愈來愈依賴網際網路所帶來的便利性,例如:透過網際網路查詢或獲取用戶感興趣的內容等。而將地理位置這項屬性作為社交網路的一部分,已經被廣泛地運用在各種生活場景當中,像是我們經常看到的打卡功能。近年來,興趣點推薦系統得到了廣泛的研究,主要目標就是為了提供用戶感興趣的地點,而該如何為用戶提供更加個性化的興趣點推薦內容,也是本論文的主要研究動機。
為了增強興趣點推薦系統的個性化程度及準確率,本研究考慮了用戶偏好的興趣點類別屬性,並提出一種基於用戶偏好興趣點類別的改良式興趣點推薦方法,該方法的主要概念是,假設用戶經常訪問餐廳類別的興趣點時,系統將優先推薦同屬於餐廳類別的興趣點給該用戶。本研究所提出的方法主要可分為兩部分:第一部分,是重新定義原始資料集所提供的興趣點類別,目的在於簡化原始提供的興趣點類別。第二部分,則是計算用戶對各類別的偏好分數(User Preference Category Score,簡稱UPCS),這裡一共可分為四個步驟:步驟一,先透過簽到資料計算用戶對各類別的簽到次數;步驟二,計算用戶對各類別的偏好分數;步驟三,計算用戶前三喜好類別(非必要);步驟四,將用戶對各類別的偏好分數轉換成用戶對各興趣點的偏好分數。最後使用這些計算出的結果作為權重,調整現有推薦系統的推薦分數。
根據實驗分析,證實考慮用戶偏好的興趣點類別屬性確實可提升現有興趣點推薦系統的性能,在Foursquare資料集加入UPCS後整體性能平均約可以提升7%,在Yelp資料集則可以提升5%。另外,本研究也針對興趣點類別的分類方法和結果進行分析,若可以讓興趣點類別均勻分布,則有機會讓UPCS發揮更大的效益。
With the proliferation of social networks and mobile devices, people are increasingly reliant on the convenience brought by the Internet, such as searching for information or accessing content of interest. Incorporating the attribute of geographical location as part of social networks has been widely applied in various real-life scenarios, as seen in popular features like check-ins. In recent years, Point of Interest (POI) recommendation systems have received extensive research attention, aiming to provide users with places of interest. The main motivation of this thesis is to explore how to offer users more personalized POI recommendations.
To enhance the personalization and accuracy of POI recommendation systems, this study considers the user preferences on interest categories and proposes an improved recommendation method based on user preference. The proposed method consists of two main parts: the first part involves redefining the POI categories in order to simplify the provided categories. The second part involves calculating the user preference category score (UPCS), which can be divided into four steps: Step 1: calculate the user's check-in frequency for each category using check-in data; Step 2: calculate the user's preference scores for each category; Step 3: determine the user's top three preferred categories (optional); Step 4: converting the user's preference scores for each category into preference scores for individual interest points. Finally, the calculated results are used as weights to adjust the recommendation scores of the existing recommendation system.
Experimental analysis confirms that considering the user's preferred POI categories can indeed improve the performance of existing POI recommendation systems. After incorporating UPCS into the Foursquare dataset, the overall performance is improved by an average of 7%, while the Yelp dataset shows an improvement of 5%. Additionally, this study analyzes the classification methods and results of interest point categories, suggesting that achieving a more balanced distribution of interest point categories may potentially yield greater benefits from UPCS.
[1] "Yelp Open Dataset." https://www.yelp.com.tw/dataset (accessed 2023).
[2] Z. Cai, G. Yuan, S. Qiao, S. Qu, Y. Zhang, and R. Bing, "FG-CF: Friends-aware graph collaborative filtering for POI recommendation," Neurocomputing, Vol. 488, pp. 107-119, 2022.
[3] E. Cho, S. A. Myers, and J. Leskovec, "Friendship and mobility: user movement in location-based social networks," KDD '11: Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 1082-1090, 2011.
[4] Y. Cui, H. Sun, Y. Zhao, H. Yin, and K. Zheng, "Sequential-knowledge-aware next POI recommendation: A meta-learning approach," ACM Transactions on Information Systems (TOIS), Vol. 40, No. 2, pp. 1-22, 2021.
[5] S. Dixon. "Number of social media users worldwide from 2017 to 2027." https://www.statista.com/statistics/278414/number-of-worldwide-social-network-users/ (accessed 2023).
[6] Z. Ebrahimpour, W. Wan, J. L. Velázquez García, O. Cervantes, and L. Hou, "Analyzing social-geographic human mobility patterns using large-scale social media data," ISPRS International Journal of Geo-Information, Vol. 9, No. 2, p. 125, 2020.
[7] C. Fu, W. Zhou, J. Wen, X. Guo, and Y. Chang, "Leveraging GCN and User Friendship for Next POI Recommendation," MLNLP '22: Proceedings of the 2022 5th International Conference on Machine Learning and Natural Language Processing, pp. 222-228, 2022.
[8] X. Jiao, Y. Xiao, W. Zheng, H. Wang, and C.-H. Hsu, "A novel next new point-of-interest recommendation system based on simulated user travel decision-making process," Future generation computer systems, Vol. 100, pp. 982-993, 2019.
[9] Y. Li, Z. Fan, D. Yin, R. Jiang, J. Deng, and X. Song, "HMGCL: Heterogeneous multigraph contrastive learning for LBSN friend recommendation," World Wide Web, pp. 1-24, 2022.
[10] B. Liu, Q. Meng, H. Zhang, K. Xu, and J. Cao, "VGMF: visual contents and geographical influence enhanced point‐of‐interest recommendation in location‐based social network," Transactions on Emerging Telecommunications Technologies, Vol. 33, No. 6, p. e3889, 2022.
[11] X. Liu, Y. Liu, K. Aberer, and C. Miao, "Personalized point-of-interest recommendation by mining users' preference transition," CIKM '13: Proceedings of the 22nd ACM international conference on Information & Knowledge Management, pp. 733-738, 2013.
[12] Y. Liu, T.-A. N. Pham, G. Cong, and Q. Yuan, "An experimental evaluation of point-of-interest recommendation in location-based social networks," Proceedings of the VLDB Endowment, Vol. 10, No. 10, pp. 1010-1021, 2017.
[13] H. C. M. Senefonte, M. R. Delgado, R. Lüders, and T. H. Silva, "Predictour: Predicting mobility patterns of tourists based on social media user’s profiles," IEEE Access, Vol. 10, pp. 9257-9270, 2022.
[14] K. Seyedhoseinzadeh, H. A. Rahmani, M. Afsharchi, and M. Aliannejadi, "Leveraging social influence based on users activity centers for point-of-interest recommendation," Information Processing & Management, Vol. 59, No. 2, p. 102858, 2022.
[15] P. Sánchez and A. Bellogín, "Point-of-interest recommender systems based on location-based social networks: a survey from an experimental perspective," ACM Computing Surveys (CSUR), Vol. 54, No. 11s, pp. 1-37, 2022.
[16] J. C. Valverde-Rebaza, M. Roche, P. Poncelet, and A. de Andrade Lopes, "The role of location and social strength for friendship prediction in location-based social networks," Information Processing & Management, Vol. 54, No. 4, pp. 475-489, 2018.
[17] H. Wang, H. Shen, W. Ouyang, and X. Cheng, "Exploiting POI-Specific Geographical Influence for Point-of-Interest Recommendation," IJCAI-18: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, pp. 3877-3883, 2018.
[18] H. Wang, M. Terrovitis, and N. Mamoulis, "Location recommendation in location-based social networks using user check-in data," SIGSPATIAL'13: Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, pp. 374-383, 2013.
[19] W. Wang, J. Chen, J. Wang, J. Chen, J. Liu, and Z. Gong, "Trust-enhanced collaborative filtering for personalized point of interests recommendation," IEEE Transactions on Industrial Informatics, Vol. 16, No. 9, pp. 6124-6132, 2019.
[20] X. Wang, F. Fukumoto, J. Li, D. Yu, and X. Sun, "STaTRL: Spatial-temporal and text representation learning for POI recommendation," Applied Intelligence, Vol. 53, No. 7, pp. 8286-8301, 2023.
[21] D. Yang, B. Qu, J. Yang, and P. Cudré-Mauroux, "Lbsn2vec++: Heterogeneous hypergraph embedding for location-based social networks," IEEE Transactions on Knowledge and Data Engineering, Vol. 34, No. 4, pp. 1843-1855, 2020.
[22] D. Yang, B. Qu, J. Yang, and P. Cudre-Mauroux, "Revisiting user mobility and social relationships in lbsns: a hypergraph embedding approach," WWW '19: The World Wide Web Conference, pp. 2147-2157, 2019.
[23] M. Ye, P. Yin, W.-C. Lee, and D.-L. Lee, "Exploiting geographical influence for collaborative point-of-interest recommendation," SIGIR '11: Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval, pp. 325-334, 2011.
[24] H. Yin, W. Wang, H. Wang, L. Chen, and X. Zhou, "Spatial-aware hierarchical collaborative deep learning for POI recommendation," IEEE Transactions on Knowledge and Data Engineering, Vol. 29, No. 11, pp. 2537-2551, 2017.
[25] D. Yu, W. Wanyan, and D. Wang, "Leveraging contextual influence and user preferences for point-of-interest recommendation," Multimedia Tools and Applications, Vol. 80, pp. 1487-1501, 2021.
[26] P. Zhao et al., "Where to go next: A spatio-temporal gated network for next poi recommendation," IEEE Transactions on Knowledge and Data Engineering, Vol. 34, No. 5, pp. 2512-2524, 2020.