Feature-Based Sentimental Analysis on Public Attention towards COVID-19 Using CUDA-SADBM Classification Model

Abstract

The COVID-19 pandemic has spread to almost all countries of the World and affected people both mentally and economically. The primary motivation of this research is to construct a model that takes reviews or evaluations from several people who are affected with COVID-19. As the number of cases has accelerated day by day, people are becoming panicked and concerned about their health. A good model may be helpful to provide accurate statistics in interpreting the actual records about the pandemic. In the proposed work, for sentimental analysis, a unique classifier named the Sentimental DataBase Miner algorithm (SADBM) is used to categorize the opinions and parallel processing, and is applied on the data collected from various online social media websites like Twitter, Facebook, and Linkedin. The accuracy of the proposed model is validated with trained data and compared with basic classifiers, such as logistic regression and decision tree . The proposed algorithm is executed on CPU as well as GPU and calculated the acceleration ratio of the model. The results show that the proposed model provides the best accuracy compared with the other two models, i.e., 96% (GPU).

Sentiment Analysis: An ERNIE-BiLSTM Approach to Bullet Screen Comments

“…This study applies four evaluation metrics as the measurement standards of this experiment to evaluate the performance of the artificial neural network model, including accuracy rate, precision rate, recall rate, and F-score [ 38 , 39 , 40 ]. True positive ( TP ) means that the predicted sentiment and the actual sentiment are both positive.…”

Fake News Detection Model on Social Media by Leveraging Sentiment Analysis of News Content and Emotion Analysis of Users’ Comments

“…Another study has indicated that many people have difficulty distinguishing between fake news and real news, irrespective of their gender, age, or educational attainment [ 10 ]. Social media platforms have presented a virtual environment for posting [ 11 ], discussion, exchange of views, and global interaction among users [ 12 ], without restrictions on location, time, or content volume [ 13 ]. A survey conducted in 2017 claimed that 67% of people in the US got their news mainly from social media [ 14 ].…”