Knowledge Discovery from Recommender Systems using Deep Learning

Abstract

Knowledge discovery of educational data plays prominent role in the process of making decisions in order to deliver correct educational reforms. knowledge discovery can be done to extract students' sentiments towards learning behavior of the course, difficulties faced, time spent for the course duration in learning the concepts and worries or fears of students like whether they may pass or fail the final exam. As student feedback is essential to assess the effectiveness of learning technologies, the hidden knowledge of students can be discovered by conducting survey or feedback form or online course satisfaction survey at the end of the courses in order to obtain the meaningful information so that, necessary steps can be taken to improve the learning process. The prime motto of our research is to discover the knowledge from the twitter data and analyze public sentiments towards education using deep learning techniques and discovering the best technique which yields optimal results. Therefore, we propose a model based on deep learning approach to discover knowledge from educational tweets. In this paper efficiency of knowledge learnt by MLP and CNN is compared with DTREE.