A new user behavior evaluation method in online social network

摘要

Due to the limitations of existing user evaluation in online social network (OSN), a new user behavior evaluation model is proposed. Considering the high degree of uncertainty, complexity, dynamics of user behavior in OSN, cloud model theory is innovatively introduced to evaluate the user behavior, on this basis, a credible evaluation scheme concerning user behavior combined with entropy weighting is proposed in this paper. The user's original behavior is classified as the evaluation factors according to the attribute, then the behavior attribute cloud is established via Reverse Cloud Generator algorithm; At the same time, the user is divided into different trust levels according to the actual situation, and hierarchical cloud is generated through Positive Cloud Generator algorithm. The membership matrix of the behavior attribute cloud to the hierarchical cloud is calculated by employing a mathematical formula, and the weight of each attribute is adaptively calculated by the entropy method, overcoming the limitations of subjective weight assignation. This model provides a new thinking of user behavior evaluation in OSN, meanwhile, also expands the application of cloud model theory and fuzzy comprehensive evaluation method. Finally, as an example of embodiment, a case study is presented for user behavior evaluation in Facebook, both the feasibility and effectiveness are verified. (C) 2019 Published by Elsevier Ltd.