A computer-implemented system for identifying the existence and position of text in visual media content and determining a subject's level of interaction with the identified text, the system comprising a computer-readable storage medium, the computer-readable storage medium comprising one or more computer-readable instructions which when executed by a processor cause the processor to:
- identify a portion of visual media content that constitutes text;
- determine a position of the identified text of the visual media content;
- present the visual media content to a subject;
- collect eye data from the subject while the subject is viewing the visual media content, the eye data including pupil data, blink data, and gaze data;
- generate a gaze pattern of the subject based on the collected eye data;
- determine whether the subject has interacted with the identified text based at least on the determined position of the identified text and the generated gaze pattern;
- and
- in response to a determination that the subject has interacted with the identified text:
- determine the subject's level of interaction with the identified text;
- and
- (ii) determine the subject's emotional response to the identified text.