Research on Point of Interest Recommendation Algorithm Based on Spatial Clustering
AUTHORS
Liguo Zheng,Dept. of Computer and Information Engineering School, Harbin Normal University, China
ABSTRACT
In order to solve the problem of recommendation of points of interest, this paper proposes an algorithm of recommendation of points of interest based on user check-in space clustering. According to the administrative region information of interest points in LBSN and the distribution characteristics of user check-in, a new spatial clustering algorithm is designed in this paper. First, according to the distribution of user check-ins, the whole data set was clustered in cities, and the user rating information was normalized. Then the recommendation scores of candidate recommendation points were calculated according to the user preference model, social relation model and geographical correlation model. The final recommendation list is obtained by calculating the recommendation probability of the points of interest. Experiments on the Yelp data set show that the proposed algorithm has higher precision and recall rate than the traditional algorithm.
KEYWORDS
LBSN, POI, Recommendation algorithm, Space clustering, YELP
REFERENCES
[1] Julong Pan, Zhengwei Zuo, Zhanyi Xu, and Qun Jin, “Privacy protection for LBS in mobile environments: progresses, issues and challenges,” International Journal of Security and Its Applications, vol.9, no.1, January, pp.249-258, (2015) DOI:10.14257/ijsia.2015.9.1.24(CrossRef)(Google Scholar)
[2] Jinying Jia and Fengli Zhang, “Non-deterministic K-anonymity Algorithm Based Untrusted Third Party for Location Privacy Protection in LBS,” International Journal of Security and Its Applications, vol.9, no.9, pp.387-400, (2015) DOI:10.14257/ijsia.2015.9.9.33(CrossRef)(Google Scholar)
[3] Jeong-Sig Kim, Eung-Sung Kim, and Jin-Hong Kim, “Bayesian Model-based Personalized Recommendation Service,” International Journal of u - and e - Service, Science and Technology, vol.10, no.7, July, pp.55-64, (2017) DOI:10.14257/ijunnesst.2017.10.7.06(CrossRef)(Google Scholar)
[4] Woo-Soo Jeong, Seung-Woan Chai, and Kyoungsik Min, “An analysis of the economic effects for the lbs-related industry in Korea,” International Journal of u - and e - Service, Science and Technology, vol.10, no.9, pp.145-150, (2017) DOI:10.14257/ijunnesst.2017.10.9.15(CrossRef)(Google Scholar)
[5] Zhang C and Wang K., “POI recommendation through cross-region collaborative filtering,” Knowledge & Information Systems, vol.46, no.2, pp.369-387, (2016)
[6] Zhang J D, Chow C Y, and Zheng Y., “ORec: An opinion-based point-of-interest recommendation framework,” In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. Melbourne: ACM Press, pp.1641-1650, (2015)
[7] Burke R., “Hybrid recommender systems: Survey and experiments,” User Modeling and User-Adapted Interaction, vol.12, no.4, pp.331-370, (2002)
[8] Yang S, Huang G, and Xiang Y, et al., “Modeling user preferences on spatiotemporal topics for point-of-interest recommendation,” In Proceeding of 2017 IEEE International Conference on Services Computing. Honolulu: IEEE Press, pp.204-211, (2017)
[9] Son J and Kim S B, “Content-based filtering for recommendation systems using multiattribute networks,” Expert Systems with Applications, vol.89, pp.404-412, (2017)
[10] Wen Y T, Lei P R, and Peng W C, et al., “Exploring social influence on location-based social networks,” IEEE International Conference on Data Mining. Shenzhen: IEEE Press, pp.1043-1048., (2014)
[11] Fang M Y and Dai B R., “Power of bosom friends, POI recommendation by learning preference of close friends and similar users,” Big Data Analytics and Knowledge Discovery. Porto: Springer Press, pp.179-192, (2016)
[12] Lin K, Wang J, and Zhang Z, et al., “Adaptive location recommendation algorithm based on location-based social networks,” International Conference on Computer Science & Education. Cambridge: IEEE Press, pp.137-142, (2015)
[13] Xu X, Zhao P, and Liu G, et al., “A Hybrid method for POI recommendation: combining check-in count, geographical information and reviews,” Asia-Pacific Web Conference. Suzhou: Springer Press, pp.162-173, (2016)
[14] Zheng Z, Chen Y, and Chen S, et al., “Location-Aware POI recommendation for indoor space by exploiting wifi logs,” Mobile Information Systems, 2017(9601404), pp.1-16, (2017)