Systems and methods are described to enact machine-based, simultaneous classification of emotional and cognitive states of an individual in substantially real time. A bootstrap approach is used to identify indicators of emotional state, including boredom, engagement and feeling overwhelmed, by finding additional interactions temporally adjacent to known indicators. A similar bootstrap approach is used to identify new indicators of knowledge acquisition (or confusion), by locating frequent temporally adjacent interactions. Systems and methods may enhance teaching by identifying knowledge presentations that result in successful knowledge acquisition, and learning by allowing instructors associated with an individual to track materials that have been understood (or misunderstood). Machine-based tracking of learning may circumvent boredom by avoiding needless repetition, and facilitate teaching of synergistic topics related to materials recently understood. Systems and methods may provide for an enhanced, individualized environment for both emotional and cognitive development.