Abstract:Call detail records contain rich spatio-temporal information and social information, which partly reflect users' habits and social pattern. It is of great significance for the study of mobile communication user profiling. Our study is based on a monthly call detail records of 10 000 subscribers provided by a Chinese telecom operator. In this study, on the one hand, we extract the moving distance, the radius of gyration, the number of access points, and the entropy of moving directions to characterize user's mobile pattern. On the other hand, we extract the call duration, the number of contact, the ratio of calling, and the entropy of sociality to characterize user's social life. Then users are divided into groups and each user gets a word cloud card based on these features. So the portrait study of mobile communication users is completed. Our work is a promising step towards inferring user attributes and understanding user characteristics using call detail records.