Techniques for enhanced media experience

One or more non-transitory computer-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to provide supplemental content along with source media by performing steps comprising:

• receiving source media and content metadata associated with the source media;
• generating supplemental content based on a subset of the content metadata that is associated with a first portion of the source media and preferences of one or more media consumers, wherein the generated supplemental content does not include the first portion of the source media;
• delivering the generated supplemental content along with the first portion of the source media to the one or more media consumers;
• receiving video sensor data captured by one or more video sensors that indicates a first reaction of the one or more media consumers to at least one of the first portion of the source media or the supplemental content;
• determining at least one of a first emotional state of the one or more media consumers, a first sentiment state of the one or more media consumers, or a first level of engagement of the one or more media consumers based on the video sensor data indicating the first reaction;
• and
• generating additional supplemental content based on the at least one of the first emotional state, the first sentiment state, or the first level of engagement.

A computing device, comprising:

• a memory;
• and
• one or more processors coupled to the memory;
• wherein the one or more processors are configured to:
• receive source media and content metadata associated with the source media;
• generate a virtual companion based on the content metadata and preferences of one or more media consumers;
• generate supplemental content to be delivered by the virtual companion, wherein the supplemental content is generated based on a subset of the content metadata that is associated with a first portion of the source media and does not include the first portion of the source media;
• have the virtual companion deliver the generated supplemental content to the one or media consumers along with the first portion of the source media;
• receive video sensor data captured by one or more video sensors that indicates a first reaction of the one or more media consumers to at least one of the first portion of the source media or the generated supplemental content;
• determine at least one of a first emotional state of the one or more media consumers, a first sentiment state of the one or more media consumers, or a first level of engagement of the one or more media consumers based on the video sensor data indicating the first reaction, wherein the first level of engagement comprises a value on an engagement spectrum;
• and
• generate additional supplemental content based on the at least one of the first emotional state, the first sentiment state, or the value on the engagement spectrum that is determined based on the video sensor data indicating the first reaction.