Chat applications often support several communication modes, e.g., texting, voice messaging, voice/video calling, sending memes/GIFs/images, sending video messages, etc. In a group chat, a given participant may not be disposed to use every chat modality. For example, one participant may be in a quiet space and constrained to use only text messaging, another participant may be in a position to receive video but not turn on their own camera, and so on.

With user permission, this disclosure applies machine-learning techniques to detect the user’s context. Based on the context, the user-preferred input and output modes for a group chat are determined. For example, such determination of user-preferred input and output modes is based upon features such as sensor data, historical usage, etc.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.