Point-of-Interest Recommendation Based on Link Prediction in Bipartite Network

Abstract

The use of location-based social networks is increasing day by day. In these networks, users check-in Point of Interest (POI) that they like, and in a sense, they advise future users. The aim of this paper is to detect whether users from the same hometown check-in for similar POIs using the link prediction method, thus recommending new POIs. The method first models the user-POI bipartite network, and then new recommendations are generated by the link prediction method. Experiments conducted on real data in Foursquare have shown that the proposed method achieves high accuracy values.

Keywords

• Machine Learning
• Recommendation Systems
• Location Based Social Networks
• Point of Interest

İki Parçalı Ağda Bağlantı Tahminine Dayalı İlgi Çekici Nokta Tavsiyesi

Abstract

Konum tabanlı sosyal ağların kullanımı her geçen gün artmaktadır. Bu ağlarda kullanıcılar beğendikleri ilgi noktalarını (POI) check-in yapar ve bir anlamda gelecekteki kullanıcılara tavsiyelerde bulunurlar. Bu makalenin amacı, bağlantı tahmini yöntemini kullanarak aynı memleketteki kullanıcıların benzer POI'ler için check-in yapıp yapmadıklarını tespit etmek ve böylece yeni POI'ler önermektir. Yöntem önce kullanıcı-POI ikili ağını modeller ve ardından bağlantı tahmin yöntemi tarafından yeni öneriler oluşturulur. Foursquare'de gerçek veriler üzerinde yapılan testler, önerilen yöntemin yüksek doğruluk değerlerine ulaştığını göstermiştir.

Keywords

• Makine Öğrenmesi
• Tavsiye Sistemler
• Konum Tabanlı Sosyal Ağlar
• İlgi Çekici Nokta

References

1. [1] Gao, H. , Tang, J. Liu, H. (2015). Addressing the cold-start problem in location recommendation using geo-social correlations, Data Mining and Knowledge Discovery March 2015, ss. 299-323.
2. [2] Zheng, Y. (2011). Location-Based Social Networks: Users, Chapter 8.
3. [3] Noulas, A., Scellato, S., Mascolo, C., & Pontil, M. (2011). An Empirical Study of Geographic User Activity Patterns in Foursquare., Proceedings of the International AAAI Conference on Web and Social Media, cilt 5(1).
4. [4] Noulas, A. , Scellato, S. , Lambiotte, R. , Pontil, M. , Mascolo, C. (2012). A Tale of Many Cities: Universal Patterns in Human Urban Mobility, PLoS ONE, cilt 7(5) , Article e37027. DOI:10.1371/journal.pone.0037027
5. [5] Albakour, M..D., Deveaud, R. , Macdonald, C. and Ounis, I. (2014). Diversifying contextual suggestions from location-based social networks, Proceedings of the 5th Information Interaction in Context Symposium, ss. 125-134.
6. [6] Fulk, J. , Yuan ,Y. (2013). Location, Motivation, and Social Capitalization via Enterprise Social Networking, Journal of Computer-Mediated Communication, cilt 19(1), ss. 20-37.
7. [7] Gao , H. , Liu, H. (2013). Data Analysis on Location-Based Social Networks, Mobile Social Networking, ss. 165-194.
8. [8] Chang, J., Sun, E. (2011). Location 3: how users share and respond to location-based data on social networking sites, The International AAAI Conference on Web and Social Media.

9. [9] Long, X. , Joshi, J. (2013). A hits-based poi recommendation algorithm for location-based social networks, Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ss. 642-647.
10. [10] Gao, H. , Tang, J. , Liu, H. (2012c). gSCorr: modeling geo-social correlations for new check-ins on locationbased social networks , Proceedings of the 21st ACM international conference on Information and knowledge management , ss. 1582–1586.
11. [11] Ye, M. , Yin, P. , Lee, W. , Lee, D. (2011). Exploiting geographical influence for collaborative point-of-interest recommendation , nnual International ACM SIGIR Conference on Research and Development in, Information Retrieval, ss. 325-334.
12. [12] Bütün, E., Kaya, M. (2020). Predicting citation count of scientists as a link prediction problem. IEEE Transactions on Cybernetics, 50(10), 4518-4529.
13. [13] Bütün, E., Kaya, M. (2019). A pattern based supervised link prediction in directed complex networks. Physica A: Statistical Mechanics and its Applications, 525, 1136-1145.
14. [14] Aslan, S., Kaya, M. (2018). Topic recommendation for authors as a link prediction problem. Future Generation Computer Systems, 89, 249-264.
15. [15] Biau, G., & Scornet, E. (2016). A random forest guided tour. Test, 25(2), 197-227.
16. [16] Destek Vektör Makineleri. https://veribilimcisi.com/2017/07/19/destek-vektor-makineleri-support-vector-machine/
17. [17] Performans Ölçütleri. https://veribilimcisi.com/2017/07/14/dogruluk-olcumu-nasil-yapilir-accuracy-measure/
18. [18] Gao H, Barbier G, Goolsby R (2011). Harnessing the crowdsourcing power of social media for disaster relief, Intelligent Systems, IEEE, cilt 26(3), ss. 10-14.