content moderation

In recent years, social media companies have grappled with defining and enforcing content moderation policies surrounding political content on their platforms, due in part to concerns about political bias, disinformation, and polarization. These policies have taken many forms, including disallowing political advertising, limiting the reach of political topics, fact-checking political claims, and enabling users to hide political content altogether. However, implementing these policies requires human judgement to label political content, and it is unclear how well human labelers perform at this task, or whether biases affect this process. Therefore, in this study we experimentally evaluate the feasibility and practicality of using crowd workers to identify political content, and we uncover biases that make it difficult to identify this content. Our results problematize crowds composed of seemingly interchangeable workers, and provide preliminary evidence that aggregating judgements from heterogeneous workers may help mitigate political biases. In light of these findings, we identify strategies to achieving fairer labeling outcomes, while also better supporting crowd workers at this task and potentially mitigating biases.

An estimated 100,000 people work today as commercial content moderators. These moderators are often exposed to disturbing content, which can lead to lasting psychological and emotional distress. This literature review investigates moderators’ psychological symptomatology, drawing on other occupations involving trauma exposure to further guide understanding of both symptoms and support mechanisms. We then introduce wellness interventions and review both programmatic and technological approaches to improving wellness. Additionally, we review methods for evaluating intervention efficacy. Finally, we recommend best practices and important directions for future research. Content Warning: we discuss the intense labor and psychological effects of CCM, including graphic descriptions of mental distress and illness.

Crowdsourced labeling of political social media content is an area of increasing interest, due to the contextual nature of political content. However, there are substantial risks of human biases causing data to be labelled incorrectly, possibly advantaging certain political groups over others. Inspired by the social computing theory of social translucence and findings from social psychology, we built PairWise, a system designed to facilitate interpersonal accountability and help mitigate biases in political content labelling.