Users in online social media tend to share their life via social networks and location checkin
actions. Thus Location-based Social Network (LBSN) data can be formed accordingly.
While LBSN has been exploited for applications such as Point-of-Interest (PoI) recommendation
and social link prediction, an emerging task is Location Promotion, i.e., finding opinion
leaders to promote a sepcific PoI. In this work, we propose and tackle two novel tasks,
Targeted Influencer Prediction (TIP) and Targeted Visitor Prediction (TVP), in the context
of Location Promotion. Given a target POI l to be promoted, TIP aims at predicting a set
of influential users who can attract more users to visit l in the future, while TVP is to find a
set of potential users who will visit l in the future. To deal with TIP and TVP, we propose a
novel graph embedding method, LBSN2vec. The main idea of LBSN2vec is to learn a lowdimentional
feature representation for each user and each location in an LBSN. In order to
effectively find the reasonable context of each node for LBSN2vec, we devise a new weighted
and penalized random walk mechanism. Equipped with the learned embedding vectors, we
propose two similarity-based measures, Attractiveness and Visiting scores, to predict the influencers
and potential visitors. Experiments conducted on a large-scale Instagram LBSN
dataset exhibit that LBSN2vec and its variant can significantly outperform state-of-the-art
graph embedding methods in both tasks of TIP and TVP.

[1] Deepak P Ankita Likhyani, Srikanta Bedathur. Locate: Influence quantification for location
promotion in location-based social networks. Proceedings of the Twenty-Sixth International
Joint Conference on Artificial Intelligence (IJCAI), pages 2259–2265, 2017.
[2] Panagiotis Bouros, Dimitris Sacharidis, and Nikos Bikakis. Regionally influential users
in location-aware social networks. Proceedings of the 22Nd ACM SIGSPATIAL International
Conference on Advances in Geographic Information Systems (SIGSPATIAL),
pages 501–504, 2014.
[3] Shanshan Feng, Gao Cong, Bo An, and Yeow Meng Chee. Poi2vec: Geographical
latent representation for predicting future visitors. Proceedings of Thirty-First AAAI
Conference on Artificial Intelligence (AAAI), pages 102–108, 2017.
[4] Shanshan Feng, Xutao Li, Yifeng Zeng, Gao Cong, Yeow Meng Chee, and Quan Yuan.
Personalized ranking metric embedding for next new POI recommendation. Proceedings
of the 24th International Conference on Artificial Intelligence (IJCAI), pages 2069–
2075, 2015.
[5] Aditya Grover and Jure Leskovec. Node2vec: Scalable feature learning for networks.
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
(IJCAI), pages 855–864, 2016.
[6] David Kempe, Jon Kleinberg, and Éva Tardos. Maximizing the spread of influence
through a social network. Proceedings of the Ninth ACM SIGKDD International Conference
on Knowledge Discovery and Data Mining (KDD), pages 137–146, 2003.
[7] Guoliang Li, Shuo Chen, Jianhua Feng, Kian-lee Tan, and Wen-syan Li. Efficient
location-aware influence maximization. Proceedings of the 2014 ACM SIGMOD International
Conference on Management of Data (SIGMOD), pages 87–98, 2014.
[8] Huayu Li, Yong Ge, Richang Hong, and Hengshu Zhu. Point-of-interest recommendations:
Learning potential check-ins from friends. Proceedings of the 22Nd ACM
SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD),
pages 975–984, 2016.
[9] Xutao Li, Gao Cong, Xiao-Li Li, Tuan-Anh Nguyen Pham, and Shonali Krishnaswamy.
Rank-geofm: A ranking based geographical factorization method for point of interest
recommendation. Proceedings of the 38th International ACM SIGIR Conference on
Research and Development in Information Retrieval (SIGIR), pages 433–442, 2015.
[10] Defu Lian, Cong Zhao, Xing Xie, Guangzhong Sun, Enhong Chen, and Yong Rui. Geomf:
Joint geographical modeling and matrix factorization for point-of-interest recommendation.
Proceedings of the 20th ACM SIGKDD International Conference on
Knowledge Discovery and Data Mining (KDD), pages 831–840, 2014.
[11] Yi Liao, Wai Lam, Shoaib Jameel, Steven Schockaert, and Xing Xie. Who wants to
join me?: Companion recommendation in location based social networks. Proceedings
of the 2016 ACM International Conference on the Theory of Information Retrieval
(ICTIR), pages 271–280, 2016.
[12] Yuanliu Liu, Pengpeng Zhao, Victor S. Sheng, Zhixu Li, An Liu, Jian Wu, and Zhiming
Cui. RPCV: recommend potential customers to vendors in location-based social network.
Proceedings of International Conference on Web-Age Information Management
(WAIM), 9098:272–284, 2015.
[13] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient estimation of
word representations in vector space. CoRR, abs/1301.3781, 2013.
[14] Xin Rong. word2vec parameter learning explained. CoRR, abs/1411.2738, 2014.
[15] Mohamed Sarwat, Ahmed Eldawy, Mohamed F. Mokbel, and John Riedl. PLUTUS:
leveraging location-based social networks to recommend potential customers to
venues. Proceedings of IEEE 14th International Conference on Mobile Data Management
(MDM), pages 26–35, 2013.
[16] Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei. Line:
Large-scale information network embedding. Proceedings of the 24th ACM International
Conference on World Wide Web (WWW), pages 1067–1077, 2015.
[17] Hongwei Wang, Jia Wang, Jialin Wang, Miao Zhao, Weinan Zhang, Fuzheng Zhang,
Xing Xie, and Minyi Guo. Graphgan: Graph representation learning with generative
adversarial nets. Proceedings of the 32nd AAAI Conference on Artificial Intelligence
(AAAI), abs/1711.08267, 2017.
[18] Min Xie, Hongzhi Yin, Hao Wang, Fanjiang Xu, Weitong Chen, and Sen Wang. Learning
graph-based poi embedding for location-based recommendation. Proceedings of the
25th ACM International on Conference on Information and Knowledge Management
(CIKM), pages 15–24, 2016.
[19] Jia-Dong Zhang and Chi-Yin Chow. Geosoca: Exploiting geographical, social and
categorical correlations for point-of-interest recommendations. Proceedings of the 38th
International ACM SIGIR Conference on Research and Development in Information
Retrieval (SIGIR), pages 443–452, 2015.
[20] Wei Zhang and Jianyong Wang. A collective bayesian poisson factorization model for
cold-start local event recommendation. Proceedings of the 21th ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining (KDD), pages 1455–
1464, 2015.
[21] Wen-Yuan Zhu, Wen-Chih Peng, Ling-Jyh Chen, Kai Zheng, and Xiaofang Zhou. Modeling
user mobility for location promotion in location-based social networks. Proceedings
of the 21th ACM SIGKDD International Conference on Knowledge Discovery and
Data Mining (KDD), pages 1573–1582, 2015.