Systems and methods for conversations with devices about media using interruptions and changes of subjects

A system for mimicking human interactions in computer systems that use interactive vocal conversations when providing media guidance by automatically interrupting and changing subjects during the interactive vocal conversation in response to detecting user hesitations, the system comprising:

• detection circuitry configured to receive a first voice input and a second voice input;
• a user interface configured to generate a first response to the first voice input, comprising a media asset recommendation associated with a first topic, and a second response, comprising a media asset recommendation associated with the first topic, to the first voice input, wherein the second voice input is followed by a period of silence and is received subsequent to the first response;
• a database of topics comprising a semantic network indicating relationships between a plurality of topics;
• and
• control circuitry configured to:
• access the database of topics;
• identify the first topic from the database of topics that is associated with the first voice input;
• and
• determine that the period of silence exceeds a threshold period of silence;
• compare the second voice input to a list of interruption inputs in response to determining that the period of silence exceeds the threshold period of silence, wherein the list of interruption inputs corresponds to a list of verbal cues indicative of hesitations, to determine a match indicative of a hesitation between the second voice input and an interruption input from the list of interruption inputs;
• and
• wherein the second response is generated by the user interface in response to determining the match between the second voice input and the interruption input, and wherein the second response is associated with the second topic from the database of topics that is associated with the first topic.