Trust evaluation of people and information on social media is critical for maintaining a healthy online social environment. How to evaluate the trustworthiness of users and tweets is challenging due to the complex and complicated relationships between/among users and their posts. As existing approaches use a single network to represent users, posts, and their relationships, they have the limitation to reflect the different statistical features of users and tweets, which has reduced the ability to determine the trustworthiness of users and tweets. To address this issue, we develop a trust evaluation method that models users and tweets separately in two networks that are coupled with each other via interactions. We provide mapping functions to map the statistical numbers of actions of users/tweets to trust values that indicate their relevant trust degrees. The proposed method provides a configurable solution that has the capability to consider the effects of users and tweets differently in different trust ranking situations. A set of experiments are conducted against real-data collected from Twitter. The experimental results show that the proposed approach is more effective in trust evaluation compared with several baseline methods.

中文翻译：

---

CoTrRank：Twitter上的信任度排名

对社交媒体上的人员和信息的信任评估对于维持健康的在线社交环境至关重要。由于用户与其发帖之间的关系复杂而复杂，如何评估用户和推文的可信赖性具有挑战性。由于现有方法使用单个网络来表示用户，帖子及其关系，因此它们在反映用户和推文的不同统计特征方面存在局限性，这降低了确定用户和推文可信度的能力。为了解决此问题，我们开发了一种信任评估方法，该方法可以在通过交互相互耦合的两个网络中分别对用户和推文进行建模。我们提供映射功能，以将用户/推文的统计操作数映射到指示其相关信任度的信任值。所提出的方法提供了一种可配置的解决方案，该解决方案具有在不同的信任等级情况下以不同的方式考虑用户和推文的影响的能力。针对从Twitter收集的真实数据进行了一组实验。实验结果表明，与几种基准方法相比，该方法在信任评估中更有效。