Transparency in Content and Source Moderation

Abstract

Content moderation is defined as the process of screening and monitoring user-generated content online. To provide a safe environment for both users and brands, platforms must moderate content to ensure that it falls within pre-established guidelines of acceptable behavior specific to the platform and its audience. Many social media companies employ thousands of employees or volunteers to moderate content manually. These moderators discuss the nature of any questionable posts off-site and remove them if they are deemed inappropriate. Certain platforms also employ automated moderation of content through machine learning models. However, many of them often do not give users any or accurate reasons when their posts are taken down. This lack of transparency in moderation can cause users to believe that their posts were evaluated in a biased manner. To increase users’ trust in the unbiased nature of a platform and still allow for extensive and robust content moderation, we propose a novel algorithm in this chapter. An adaptive machine learning model is used as the initial moderation layer, and then users are allowed to moderate posts through a trust-based social network algorithm. Since machine learning models can gradually improve their performance through feedback and feedback is given in a self-policing fashion, the system enforces both accuracy and transparency for content moderation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.