Article Preview
Top1. Introduction
Today, Social Network Analysis (SNA) is commonly applied to investigating trends with studies of Social Media Analysis (SMA) and Machine Learning (ML) used for such purposes. During recent years, social media has become a huge part of our daily life because it connects us to the outside world. According to (Merolli et al. 2013; Berkovic et al. 2020), social media provides a unique opportunity to observe opinions, sentiments, and interactions between individuals living with chronic diseases, and to leverage this information to promote positive health outcomes. Sentiment analysis can also facilitate the healthcare industry to use reliable data for their growth by taking necessary measures. Likewise, (Kalaivani & Shunmuganathan, 2013) noted that the sentiment found within comments, feedback, or critiques provides useful indicators for many different purposes and can be categorized by polarity. Similarly, social networks are the main resources to gather information about patient’s sentiments and opinions towards different health topics as they spend hours daily on social media and share their opinions. Currently, peoples and citizens, in general, are increasingly using the Internet for searching health information and support. According to (Kamakshi, 2020), the use of online health communities is particularly popular among disease chronic patients. Surveys show that these patients significantly benefit from social interaction with peers and the sharing of knowledge and experiences. In particular, Twitter has emerged as the most influential micro-blog service with Twitter data sources gaining considerable attention among researchers. Yet, the fact that texts in social media are mostly written in colloquial language and both understanding and analyzing these texts is somewhat difficult in medical (Covid-19) context, further research attention in this area is needed, especially in text sentiment analysis. In contrast, the coronavirus disease (Covid-19) pandemic led to substantial public discussion on social media like Twitter. It is not allowing people to get through this health crisis. As well, this Covid-19 pandemic introduced various challenges with fundamentally altering the way of life for many people around the world (Pastor, 2020). For this, understanding these discussions can help governments, clinics, healthcare organizations, health services, and an individual navigates the pandemic. In addition, the tweets and opinions on Covid-19 are becoming a cause of concern which needs to be raised to handle misleading information from different sources (Sethi et al. 2020; Alhazmi & Alharbi, 2020).
In this context, social media is an important communication medium during the crisis namely the Covid-19 pandemic. Information in social media platforms like Twitter is also of great interest for researchers and professionals, as it allows for research the side effects of medicines, alternative treatments, symptoms, pandemic spread (Covid-19), and quality and pollution of the environment. However, the quantity of information is so gigantic that it is difficult for the users to find the information that is really needed. As well, we found that nearly 80% of searches demonstrate that people have tweeted mostly positive regarding Covid-19. This paper focuses on the fact that analysis sentiment on Twitter users might play an important role to understand the people behavior, emotions, assess the content and sentiment of tweets during the Covid-19 pandemic. Obviously, greater understanding and public awareness of the pandemic are still needed.
During recent years, artificial intelligence, and its most common subset known as Machine Learning (ML), is a the most effective method used in the field of data analytics in order to predict something by devising some models and algorithms (Brahami et al. 2022; Brahami et al. 2020; Anitha & Asha, 2018). Furthermore, the deep learning is a new learning technique of the machine learning, it analyze the neural network through the interpretation of the appropriate data. The deep learning architectures are helpful in finding the desired text information, so the application of deep learning plays an important role in process of handling the text.