Selected Papers of the IRIS, Issue 13 (2022)


Most predictions of user behavior occur after a user has participated in the community for a while, and those who have just registered are easily overlooked because their community characteristics have not yet been revealed. However, users are easy to be lost in the early stage. Based on the theory of social capital, this paper proposes a new approach to predict the willingness, mode, and degree of content contribution of the newly registered user based on users' information disclosure behavior aiming at reducing the churn rate of newly registered users. We crawled the data of 4 million users in the Zhihu community and deeply studied the relationship between the disclosure behavior of different types of information and the content contribution degree of users through statistical analysis methods and machine learning algorithms. The result shows that if a user discloses personal information, the probability of his in-depth response contribution and in-depth questioning contribution will increase correspondingly, and different types of information disclosure will lead to a different probability of an increase. Furthermore, In addition, users' disclosure of different types of information will lead to differences in their preference for the way they contribute content.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.