We detect toxic messages on a global online collaboration platform on a regular basis. When a message is classified as toxic, we provide a reminder about the toxicity of the message to some of the senders.
Experimental design
We detect potentially toxic messages using a state-of-the-art classifier and send reminders to a random subset of their senders. The reminders inform users that their messages may appear rude or disrespectful. We then track changes in message features and activity for up to six weeks after the intervention.
Design details
Randomization method
Randomization is done automatically by the computer at the time a user sends their first toxic message.
Randomization unit
The randomization is done at the user level.
Clusters
No cluster.
Observations
The intervention will continue until reaching 500 users per condition or eight weeks of implementation, whichever occurs first.
Arms
Equal distribution among three conditions.
Primary outcomes
Take-up and individual outcomes up to six weeks after the intervention, including features of messages and activity measures.
Secondary outcomes
Measures of collaboration and popularity, as well as the language of messages both within the thread and repository, observed up to six weeks after the intervention.
Survey responses, including opt-out behavior and willingness to subscribe (WTS) to a premium version of the platform that includes the reminder feature tested in this intervention.
Cited by
No citation data available for this registration yet.