Techniques for generating auxiliary information for a media presentation are provided. In one example, a computer-implemented method comprises receiving, by a device operatively coupled to a processor, first feedback information for a group of users regarding mental states of the users during a media presentation. The computer-implemented method can further comprise determining, by the device, first parts of the media presentation considered confusing to at least some of the users and second parts of the media presentation considered interesting to at least some of the users based on the first feedback information, and generating, by the device, an index data structure comprising first information identifying the first parts and classifying the first parts as confusing and second information identifying the second parts and classifying the second parts as interesting.