Classifying Various Types Of Symptoms Of COVID-۱۹ (CTSC) In Twitter (Text Mining)

  • سال انتشار: 1400
  • محل انتشار: اولین کنفرانس ملی سیستم های پیچیده با محوریت علم شبکه
  • کد COI اختصاصی: CSANS01_022
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 428
دانلود فایل این مقاله

نویسندگان

Mahdieh Vahedipoor

Computer Engineering Student Qom University Of Technology

Mahbobeh Shamsi

Computer Engineering Assistant Qom University Of Technology

Saba Farhadi

Computer Engineering Student Qom University Of Technology

Reza Rasouli

Computer Engineering Assistant Qom University Of Technology

چکیده

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 usemachine learning and deep learning algorithms for such analyzes. In this study, we present a method for classifying the types of symptoms of COVID-۱۹ disease (CTSC) using deep learning algorithms and then analyze English Twitter data related to people who tested positive for COVID-۱۹ for ۸ days from ۲۰۲۱/۰۶/۲۶ to ۲۰۲۱/۰۷/۰۴. This study includes pre-processing of tweets and classification of the different symptoms of COVID-۱۹, including Respiratory, Digestive, Muscular, Smell-Taste, and Sinusitis. In the proposed framework, Machine learning algorithms such as LR, DT, SGD, SVM, RF and deep learning algorithms such as CNN, LSTM, and GRU evaluate sentiment analysis. The results show that users diagnosed with covid۱۹ show respiratory symptoms, including sneezing, lung problems, sore throat, ulcers, cough, fever, shortness of breath, and heart problems ۱۸% more likely than others. We also obtained the best performance for evaluating the CTSC method using machine learning algorithms with accuracy of ۸۷% and deep learning algorithms with accuracy of ۹۶% .

کلیدواژه ها

COVID-۱۹, Respiratory, Twitter, Deep Learning, disease.

مقالات مرتبط جدید

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.