Systems and methods for enhancing responsiveness to utterances having detectable emotion

A system, comprising:

• a non-transitory memory storing instructions;
• and
• at least one processor which, when executing the instructions, operates to:
• receive a first natural utterance by a user device, the first natural utterance including a request for playback of media content;
• perform, in response to receiving the first natural utterance, a first action by the user device, the first action including playback of a media content item;
• receive, via the user device, and during the playback of the media content item, a second natural utterance;
• determine that a command is non-extractable from a textual representation of the second natural utterance;
• in response to the determine that the command is non-extractable from the textual representation of the second natural utterance, determine that the second natural utterance includes a non-textual emotion feature and extract the non-textual emotion feature from the second natural utterance;
• detect a negative feedback response based on the non-textual emotion feature;
• and
• in response to the detect a negative feedback response based on the non-textual emotion feature, perform a second action by the user device, the second action including stopping playback of the media content item.