Conversations Gone Awry: Detecting Early Signs of Conversational Failure
This addresses the challenge of antisocial behavior like harassment in online social systems, offering a proactive approach rather than reactive detection.
The paper tackles the problem of predicting conversational failure in online discussions from the start, aiming to enable early intervention, and demonstrates feasibility in detecting early warning signs of antisocial behavior.
One of the main challenges online social systems face is the prevalence of antisocial behavior, such as harassment and personal attacks. In this work, we introduce the task of predicting from the very start of a conversation whether it will get out of hand. As opposed to detecting undesirable behavior after the fact, this task aims to enable early, actionable prediction at a time when the conversation might still be salvaged. To this end, we develop a framework for capturing pragmatic devices---such as politeness strategies and rhetorical prompts---used to start a conversation, and analyze their relation to its future trajectory. Applying this framework in a controlled setting, we demonstrate the feasibility of detecting early warning signs of antisocial behavior in online discussions.