A Hybrid Deep Learning Technique for Sentiment Analysis in E-Learning Platform with Natural Language Processing

E-learning-based teaching methodologies are increasing now-a-days and also, the online classes are considered as highly popular that ensures the virtual platform for online education from anywhere in the world. The social networks are widely distributed that generates different opinions on various perspectives of life through the messages on the web. This textural information is highly sourced with the data for performing the sentiment analysis and opinion mining that is expressed through the text. This text provides the feelings of the students with the statements that show agreement or disagreement in the comment sections to reveal the negative or positive feelings of the students towards the learning. The major goal of this paper is to design of new sentiment analysis model for e-learning platform with the help of natural language processing techniques. Initially, the standard text data regarding e-learning platform with user reviews are gathered from benchmark resources. The gathered data is forwarded to pre-processing technique, where the unnecessary content is avoided for maximizing the performance of sentiment analysis. Further, word to vector conversion is carried out using glove embedding scheme for getting the relevant data for sentiment analysis. Further, the sentiment classification is carried out by Convolutional Neural Networks (CNN) with Gated Recurrent Unit (GRU). Finally, the sentiments are analyzed through hybrid deep learning in the field of e-learning. The investigation reveals promising results in sentiment analysis tasks.