| Classifying Various Types Of Symptoms Of COVID-19 (CTSC) In Twitter Using Deep Learning Algorithms |
| کد مقاله : 1022-CSANS2022 |
| نویسندگان: |
|
محبوبه شمسی *، مهدیه واحدی پور، صبا فرهادی، عبدالرضا رسولی دانشگاه صنعتی قم |
| چکیده مقاله: |
| Data mining has many usages in the field of health, including the diagnosis of diseases, classification of patients in disease management, finding patterns for faster diagnosis of patients, and preventing complications. Research in the field of extracting public health data in social networks such as Twitter has grown exponentially. Many researchers have decided to use machine learning and deep learning algorithms for such analyzes. In this study, we present a method for classifying the types of symptoms of COVID-19 disease (CTSC) using deep learning algorithms and then analyze English Twitter data related to people who tested positive for COVID-19 for 8 days from 2021/06/26 to 2021/07/04. This study includes pre-processing of tweets and classification of the different symptoms of COVID-19, including Respiratory, Digestive, Muscular, Smell-Taste, and Sinusitis. In the proposed framework, deep learning algorithms such as CNN, LSTM, and GRU evaluate sentiment analysis. The results show that users diagnosed with covid19 show respiratory symptoms, including sneezing, lung problems, sore throat, ulcers, cough, fever, shortness of breath, and heart problems 18% more likely than others. We also obtained the best performance for evaluating the CTSC method by deep algorithms with 96% accuracy. |
| کلیدواژه ها: |
| COVID-19, Respiratory, Twitter, Deep Learning, disease. |
| وضعیت : مقاله برای ارائه شفاهی پذیرفته شده است |
