Mutual trust among social networks users encourages positive communications, so it is critical to study trust in the context of online social networks. In this study, we built a model to calculate trust of social media users. Data was collected from Qzone (Tencent Technology Co., Ltd.), a SN service (also known as QQ) in China. We identified 150 QQ users and 3 friends from each of the users; data of these users were collected by Python program. The relationship between trust and closeness was

more »

... nstructed using an ordinary least squares regression model, and the factors that influence trust between social network users were constructed using an endogenous switching regression model. We also conducted a two-stage least squares robustness analysis to confirm the results. We found that user trust and closeness are positively correlated. A user's trust is positively related to three closeness indicators: comments, @s to QQ friends (a reminder nudge for attention), and messages. Increasing closeness in social networks has a positive effect on trust formation.