PROVIDING FEEDBACK BY EVALUATING MULTI-MODAL DATA USING MACHINE LEARNING TECHNIQUES

摘要

Methods, apparatus, and processor-readable storage media for evaluations performed by applying machine learning and artificial intelligence techniques to multi-modal data are provided herein. An example computer-implemented method includes determining audio attributes associated with an instruction event by applying machine learning techniques to audio data captured in connection with the event; determining video attributes associated with the event by applying machine learning techniques to video data captured in connection with the event; determining image attributes associated with the event by applying machine learning techniques to image data captured in connection with the event; determining context-based attributes associated with the instruction event by generating and processing audience responses to dynamic context-based audience queries in connection with the event; generating an evaluation score attributed to at least one instructor of the event based at least in part on the audio attributes, video attributes, image attributes, and context-based attributes; and outputting the evaluation score.