EChat: An Emotion-Aware Adaptive UI for a Messaging App

Radha Kumaran, Viral Niraj Doshi, Sherry X. Chen, Avinash Ajit Nargund, Tobias Höllerer, Misha Sra

Abstract: While online forums provide a convenient platform for people to interact anonymously with others who share similar interests, they have to deal with large amounts of hate speech and inappropriate content, often posted by users in the heat of the moment. This can have a negative impact on the psychological state of other forum users and moderators, who are tasked to identify and delete such content. We investigate a preventative approach to this problem with the design of EChat, a proof-of-concept augmentation to online forums that helps users attend to their emotional state. The user’s current emotional state is detected using facial emotion recognition, and the aesthetics of the UI are adapted to reflect this emotion. In case of an emotion with negative valence such as anger or sadness, the UI aesthetic is gradually transitioned to one that evokes a more positive emotion. Semi-structured interviews with EChat users confirm the potential of emotion-aware design to reduce hateful content, and also highlight important design considerations.