GreaseVision: Rewriting the Rules of the Interface
This work addresses the challenge of systematic harm intervention for end-users and researchers in fast-changing digital systems, representing a novel approach rather than an incremental improvement.
The authors tackled the problem of addressing digital harms across interfaces by introducing GreaseVision, a framework that enables end-users to collaboratively develop personalized interventions using a no-code approach and few-shot machine learning, resulting in a tool that allows for both individual harm study and large-scale research on interventions.
Digital harms can manifest across any interface. Key problems in addressing these harms include the high individuality of harms and the fast-changing nature of digital systems. As a result, we still lack a systematic approach to study harms and produce interventions for end-users. We put forward GreaseVision, a new framework that enables end-users to collaboratively develop interventions against harms in software using a no-code approach and recent advances in few-shot machine learning. The contribution of the framework and tool allow individual end-users to study their usage history and create personalized interventions. Our contribution also enables researchers to study the distribution of harms and interventions at scale.