TY - GEN
T1 - Towards social user profiling
T2 - 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2012
AU - Li, Rui
AU - Wang, Shengjie
AU - Deng, Hongbo
AU - Wang, Rui
AU - Chang, Kevin Chen Chuan
PY - 2012
Y1 - 2012
N2 - Users' locations are important to many applications such as targeted advertisement and news recommendation. In this paper, we focus on the problem of profiling users' home locations in the context of social network (Twitter). The problem is nontrivial, because signals, which may help to identify a user's location, are scarce and noisy. We propose a unified discriminative influence model, named as UDI, to solve the problem. To overcome the challenge of scarce signals, UDI integrates signals observed from both social network (friends) and user-centric data (tweets) in a unified probabilistic framework. To overcome the challenge of noisy signals, UDI captures how likely a user connects to a signal with respect to 1) the distance between the user and the signal, and 2) the influence scope of the signal. Based on the model, we develop local and global location prediction methods. The experiments on a large scale data set show that our methods improve the state-of-the-art methods by 13%, and achieve the best performance.
AB - Users' locations are important to many applications such as targeted advertisement and news recommendation. In this paper, we focus on the problem of profiling users' home locations in the context of social network (Twitter). The problem is nontrivial, because signals, which may help to identify a user's location, are scarce and noisy. We propose a unified discriminative influence model, named as UDI, to solve the problem. To overcome the challenge of scarce signals, UDI integrates signals observed from both social network (friends) and user-centric data (tweets) in a unified probabilistic framework. To overcome the challenge of noisy signals, UDI captures how likely a user connects to a signal with respect to 1) the distance between the user and the signal, and 2) the influence scope of the signal. Based on the model, we develop local and global location prediction methods. The experiments on a large scale data set show that our methods improve the state-of-the-art methods by 13%, and achieve the best performance.
KW - influence model
KW - location profiling
KW - social network
UR - http://www.scopus.com/inward/record.url?scp=84866016517&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84866016517&partnerID=8YFLogxK
U2 - 10.1145/2339530.2339692
DO - 10.1145/2339530.2339692
M3 - Conference contribution
AN - SCOPUS:84866016517
SN - 9781450314626
T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
SP - 1023
EP - 1031
BT - KDD'12 - 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Y2 - 12 August 2012 through 16 August 2012
ER -