MoodSwipe: A Soft Keyboard that Suggests Messages Based on User-Specified Emotions
This work addresses the need for more convenient and emotionally-aware user interfaces in messaging apps, though it appears incremental by combining existing technologies like emotion classification and text suggestion.
The paper tackles the problem of enhancing text messaging by suggesting messages based on user-specified emotions, using real dialog data to train emotion classification models and showing that good emotion cues improve text suggestion.
We present MoodSwipe, a soft keyboard that suggests text messages given the user-specified emotions utilizing the real dialog data. The aim of MoodSwipe is to create a convenient user interface to enjoy the technology of emotion classification and text suggestion, and at the same time to collect labeled data automatically for developing more advanced technologies. While users select the MoodSwipe keyboard, they can type as usual but sense the emotion conveyed by their text and receive suggestions for their message as a benefit. In MoodSwipe, the detected emotions serve as the medium for suggested texts, where viewing the latter is the incentive to correcting the former. We conduct several experiments to show the superiority of the emotion classification models trained on the dialog data, and further to verify good emotion cues are important context for text suggestion.