Analysis of Student Sentiment Level using Perceptual Neural Boltzmann Machine Learning Approach for E-learning Applications

Gathering and analyzing feedback has long been an important topic. E-learning has become one of the most effective training methods. Specifically, e-learning is considered as a supportive and a useful way to understand students and their learning problems. The sentiment analysis systems provide recommendations for related student feedback details and play an important role in using information about disseminating e-learning projects. Sentiment analysis-based machine learning technique plays an important role in building a recommender system. It has been very difficult to identify the student interest score with the previous system and does not understand the learning problems in their automatic sentiment analysis. This proposed framework for the recommender system is based on machine learning models using sentiment analysis. Perceptual Neural Boltzmann Machine (PNBM) is used to classify sentiment score and the web data-based student feedback based automatic sentiment analysis. This study aims to develop a PNBM system-based analysis of student feedback and satisfaction by assigning proper sentiment score through student interest score based and communicating under the social media e-learning chat-based. The proposed system gives better simulation results of analysis of classification accuracy, time complexity, sensitivity and specificity, and analysis of Sysnet based sentence level.