Systems and methods for providing a multi-modal evaluation of a presentation

A computer-implemented method for providing a multi-modal evaluation of a presentation, comprising:

• generating, using a motion capture device, motion data of an examinee based on video frames, the motion data representing motion of an examinee giving a presentation;
• generating, using a processing system, a plurality of non-verbal metrics of the presentation based on the motion data, the non-verbal metrics including a metric of gesticulation;
• wherein the metric of gesticulation indicates an amount of hand gesturing and is based on a magnitude or a rate of pixel value changes between the video frames;
• generating and outputting, using the processing system, a presentation score indicating an evaluation of the presentation based on inputting the non-verbal metrics to a model comprising weights for a plurality of the non-verbal metrics, the weights being based on correlations between human scores and the non-verbal metrics for a collection of human-scored presentations.

A non-transitory computer-readable medium encoded with instructions for commanding one or more data processors to execute steps for providing a multi-modal evaluation of a presentation, comprising:

• generating, using a motion capture device, motion data of an examinee based on video frames, the motion data representing motion of an examinee giving a presentation;
• generating, using a processing system, a plurality of non-verbal metrics of the presentation based on the motion data, the non-verbal metrics including a metric of gesticulation;
• wherein the metric of gesticulation indicates an amount of hand gesturing and is based on a magnitude or a rate of pixel value changes between the video frames;
• generating and outputting, using the processing system, a presentation score indicating an evaluation of the presentation based on inputting the non-verbal metrics to a model comprising weights for a plurality of the non-verbal metrics, the weights being based on correlations between human scores and the non-verbal metrics for a collection of human-scored presentations.