基于时空感知的用户角色推理

随着大数据和信息技术的发展，更好地理解用户的行为轨迹在个性化推荐、广告推荐等方面越来越重要。该文依据大数据环境下的城市计算理论，提出一种基于情境感知的用户角色推理模型。通过用户的行为轨迹分析其行为的时空特性；结合时间、语义分析等构造识别用户角色概率推理模型；通过算法克服识别用户角色的主观性、动态适应性差等问题。实验结果证明了该文所提模型的可行性、精确性和预测准确性。

Inferring Social Roles with Spatio-temporal Awareness

With the development of big data and information technology, a better understanding of users trajectories is of great importance for the design of many applications, such as personalized recommendation, behavioral targeting and computational advertising. In this paper, with the theory of urban computing based on big data, a model of recognizing information veracity of users on the social media networks is proposed. The behavior characteristics of users trajectories based on context awareness are analyzed. The model of recognizing the truth of social roles is formalized and built. The subjectivity of recognizing users roles is overcomed. Furthermore, experiments are conducted with large-scale and real-world datasets. The results show that the proposed model offers a powerful ability for recognition of truth social roles.