Dianping Data Sets

We crawled data from a real social network-based recommender system called Dianping, which is a leading local restaurant search and review platform in China. The raw data contains information between April 2003 and November 2013. Based on it, we constructed several data sets for evaluating different recommendation tasks.

Dianping_SequentialRec (2020)

This is the anonymized Dianping dataset used in our TKDE'20 paper for evaluating sequential recommendation task. It contains 616,331 users, 10,979 restaurants and 3,868,306 actions from April 2003 to November 2013 in Shanghai, China. There are 247 restaurant categories. For privacy issue, we do not include the user information and restaurant attributes which can be used to identify a real person. Please see README file for details of data format. [download]

Dianping_SocialRec (2015)

This is part of the anonymized Dianping dataset used in our RecSys'15 paper for evaluating the quality of social recommender systems. It contains 147,918 users, 11,123 restaurants and 2,149,675 ratings from April 2003 to November 2013 in Shanghai, China. For the social friend network, there are a total of 629,618 claimed social relationships (undirected edge). For privacy issue, we do not include the user information and restaurant attributes which can be used to identify a real person. Please see README file for details of data format. [download]

Citation

If you use Dianping data sets, please cite our papers [bib]:

[1] Hui Li, Ye Liu, Nikos Mamoulis, and David S. Rosenblum, "Translation-Based Sequential Recommendation for Complex Users on Sparse Data," IEEE Transactions on Knowledge and Data Engineering (TKDE), 2020.
[2] Hui Li, Yu Liu, Yuqiu Qian, Nikos Mamoulis, Wenting Tu, and David W. Cheung, "HHMF: Hidden Hierarchical Matrix Factorization for Recommender Systems," Data Mining and Knowledge Discovery (DMKD), vol. 33, no. 6, pp. 1548-1582, 2019.
[3] Hui Li, Dingming Wu, Wenbin Tang, and Nikos Mamoulis, "Overlapping Community Regularization for Rating Prediction in Social Recommender Systems," In RecSys, pp. 27-34, 2015.
[4] Hui Li, Dingming Wu, and Nikos Mamoulis, "A Revisit to Social Network-based Recommender Systems," In SIGIR, pp. 1239-1242, 2014.