Automatic feedback captions for eye-tracker based online assessment

Abstract

In the era of Automation, there has to be a way to improvise online assessment. This paper has demonstrated a methodology to enhance the online assessment with the help of an Eye Tracker. That has the ability to categorize the behavior of the participant with the state of the art proposed within the paper. Compared with the traditional assessment, here with the help of this model, an automated feedback sentence is returned along with the score. This adds an advantage to the assessor for fair score awarding. The model has utilized an open-source eye tracker tool to capture eye movements during the assessment. Thereafter a customized classification model is used to provide the relevant keywords, out of which the sentence will be generated using a Deep Learning model.