Data Science Brown Bag Series: Tackling harmful online comments with targeted email feedback

Abstract from the speaker

Platforms that host online discourse face competing demands between allowing free speech and enforcing community guidelines meant to encourage users’ safe participation. One tool they have is content moderation, much of which is done by deleting content without providing feedback to or even notifying the offending user, making it hard for users to understand what they did wrong. In a joint project with the Swiss newspaper Blick, we test whether providing feedback after deletion affects users’ future commenting behavior. We identify toxic comments that were submitted but not published on Blick.ch and compare the default lack of feedback to three different email responses: a generic response informing users that their comment violated the guidelines, an empathy-based response encouraging them to think of the targets of their offensive content, and a norms-based response highlighting the low toxicity of other comments.

Bring your own lunch bag! Light pastries and drinks will be available in case you forget to bring it. 

—

The Data Science Brown Bag Series is an informal and interactive gathering where participants bring their own brown bag lunch and engage in discussions on research and insights the field of data and computational social science (light pastries and drinks will be available if you forget your lunch bag!). 

The series provides a platform for data enthusiasts, researchers, and practitioners to share their experiences, best practices, and emerging methodologies and research in using data science to analyze and understand social and political phenomena. The brown bag talk series is for anyone interested in data science and social science to network, learn, and share ideas in a casual and friendly setting.