At least one user expression of a first user of a first communication device, at least one text-based electronic communication sent or received by the first user, or at least one background sound detected in an environment where the first user is located can be monitored in real time. A current demeanor of the first user can be automatically determined by processing user expression, the text-based electronic communication, or the background sound. An incoming call from a second communication device to the first communication device can be detected. Responsive to detecting the incoming call, a ringback tone indicating the current demeanor of the first user can be automatically selected. The ringback tone can be communicated to the second communication device for presentation to a second user who is using the second communication device.