GEOSPATIAL SOCIAL NETWORK ANALYSIS WITH USING GIS FOR LOCATION-BASED SERVICE RECOMMENDATION

Year 2018, Volume: 19 Issue: 3, 585 - 606, 01.09.2018

Levent Sabah Mehmet Şimşek

Abstract

People can mark places they visit and share them with other people with using geospatial online social networks. Discovering socially popular locations on geospatial social networks became more important for many applications such as public transportation system planning, tourist trajectory planning etc. In the literature, there are some studies conducted for this purpose. However, most of these studies focused on only location information and ignored time data of check-in. In this study, we analyzed geospatial social network data by dividing it into time slots. Also, the vast majority of studies in the literature do not provide visual analysis results. This reduces the intelligibility of the results. Our system uses advanced heat maps to provide easy visually interpretable results. The developed system determines the tendency of the check-in intensities at the time of day and the seasons of the year. Using QGIS, which is an open source geographic information system, we obtained check-in data from dataset within Turkey country boundary. Also, Istanbul province’s check-in data was used for more specific analyzing with 3-hour ranges of a day. Furthermore, the density of spatial check-in points was obtained by using heat maps.

Keywords

Social Network Analysis, Spatial Data Analysis, Geographic Information Systems, Recommender Systems, Heat maps

References

• [1] Kefalas P, Manolopoulos Y. A time-aware spatio-textual recommender system. Expert Systems With Applications 2017; 78: 396–406.
• [2] Sun Y, Chen M, Hu L, Qian Y, Mehedi M. ASA : Against statistical attacks for privacy-aware users in Location Based Service. Future Generation Computer Systems 2017;70: 48–58.
• [3] Assem H, Xu L, Buda T S, O’Sullivan D. Spatio-Temporal Clustering Approach for Detecting Functional Regions in Cities. In: 2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI); 2016, pp. 370–377.
• [4] Sakir A, Celik M. Discovering socially important locations of social media users. Expert Systems With Applications 2017; 86(December 2015):113–124.
• [5] Celikten E, Le Falher G, Mathioudakis M.Modeling Urban Behavior by Mining Geotagged Social Data. IEEE Transactions on Big Data 2017: 3(2):220–233.
• [6] Dokuz A S, Celik M. Discovering socially important locations of social media users. Expert Systems with Applications 2017; 86(December 2012):113–124.
• [7] Cenamor I, de la Rosa T, Núñez S, Borrajo D. Planning for tourism routes using social networks. Expert Systems with Applications 2017; 69: 1–9.
• [8] Zheng Y, Zhang L, Xie X, Ma W-Y. Mining interesting locations and travel sequences from GPS trajectories. Proceedings of the 18th international conference on World wide web 2009;49:791.
• [9] Liu B, Xiong H. Point-of-Interest Recommendation in Location Based Social Networks with Topic and Location Awareness. Sdm 2013; 396–404.
• [10] Chamoso P, Rivas A, Rodríguez S, Bajo J. Relationship recommender system in a business and employment-oriented social network. Information Sciences 2018;433–434: 204–220.
• [11] Yu W. Spatial co-location pattern mining for location-based services in road networks. Expert Systems with Applications 2016; 46:324–335.
• [12] Huang Y, Shekhar S, Xiong H. Discovering colocation patterns from spatial data sets: a general approach. IEEE Transactions on Knowledge and Data Engineering 2004;16(12): 1472–1485.
• [13] Colomo-Palacios R, García-Peñalvo F J, Stantchev V, Misra S. Towards a social and context-aware mobile recommendation system for tourism. Pervasive and Mobile Computing 2017; 38: 505–515.
• [14] Sattari M, Manguoglu M, Toroslu I H, Symeonidis P, Senkul P, Manolopoulos Y. Geo-activity recommendations by using improved feature combination. Proceedings of the 2012 ACM Conference on Ubiquitous Computing (UbiComp ’12) 2012; 996–1003.
• [15] Gaete-Villegas J, Cha M, Lee D, Ko I.-Y. TraMSNET: A Mobile Social Network Application for Tourism. Proceedings of the 2012 ACM Conference on Ubiquitous Computing 2012;1004–1011.
• [16] Zheng Y, Zhang L, Ma Z, Xie X, Ma W.-Y. Recommending friends and locations based on individual location history. ACM Transactions on the Web 2011;5(1):1–44.
• [17] Yang D, Zhang D, Qu B. Participatory Cultural Mapping Based on Collective Behavior Data in Location Based Social Networks. ACM Trans. on Intelligent Systems and Technology (TIST) 2015.
• [18] Yang D, Zhang D, Chen L, Qu B. Nation Telescope: Monitoring and Visualizing Large-Scale Collective Behavior in LBSNs. Journal of Network and Computer Applications (JNCA) 2015; 55:170-180.
• [19] Yeung A K W, Hall G B. Spatial Database Systems. Springer, 2007.
• [20] Silverman B W. Density Estimation for Statistics and Data Analysis. London, UK: Chapman and Hall, 1986.
• [21] Menke K, Smith R, Pirelli L, Hoesen J V. Mastering QGIS – Second Edition. Packt, 2016.