Media manipulation using cognitive state metric analysis

A computer program product embodied in a non-transitory computer readable medium for media manipulation, the computer program product comprising code which causes one or more processors to perform operations of:

• collecting, at a client device, data on a user interacting with a media presentation that includes an advertisement, wherein the data comprises facial image data of the user;
• analyzing, using one or more processors, the facial image data to extract cognitive state content of the user;
• generating one or more emotional intensity metrics based on the cognitive state content;
• identifying a time of peak valence within the advertisement;
• optimizing the advertisement based on valence, wherein the optimizing includes deleting one or more portions of the advertisement determined to be least interesting, wherein the one or more portions determined to be least interesting are associated with absolute valence scores closest to zero;
• and
• manipulating the media presentation based on the emotional intensity metrics, the time of peak valence, and the cognitive state content, wherein the manipulating includes determining advertisement placement within the media presentation based on the cognitive state content of the user.

A computer system for media analysis comprising:

• a memory which stores instructions;
• one or more processors coupled to the memory, wherein the one or more processors, when executing the instructions which are stored, are configured to:
• collect, at a client device, data on a user interacting with a media presentation that includes an advertisement, wherein the data comprises facial image data of the user;
• analyze the facial image data to extract cognitive state content of the user;
• generate one or more emotional intensity metrics based on the cognitive state content;
• identify a time of peak valence within the advertisement;
• optimize the advertisement based on valence, wherein optimizing includes deleting one or more portions of the advertisement determined to be least interesting, wherein the one or more portions determined to be least interesting are associated with absolute valence scores closest to zero;
• and
• manipulate the media presentation based on the emotional intensity metrics, the time of peak valence, and the cognitive state content, wherein manipulation includes determining advertisement placement within the media presentation based on the cognitive state content of the user.