Article Preview
TopIntroduction
The end of the year 2019 has seen a spread of COVID-19 coronavirus in China which infected a large number of people all over the country (Li et al., 2020). However, China was soon able to control the outbreak, while there was a rapid spread of COVID-19 to other countries. At present, many countries are able to control the further spread of COVID-19, while few countries are still struggling to adopt efficient and effective mechanisms to control the pandemic. COVID-19 has adversely affected a number of sectors/industries including travel and tourism, hospitality industry (Gursoy & Chi, 2020), hotel industry (Hoisington, 2020) etc. Infact the study by Bartik et al. 2020 shows that pandemic has led to a massive dislocation of small businesses. In contrast there have been few sectors which have been benefited from the pandemic; healthcare industry being one of them.
In the difficult times of COVID-19 pandemic, our healthcare system has been continuously operating above its capacity and is in a stressed situation (Kavadi et al., 2020). This has not only affected the healthcare workers but also patients who are in immediate need of medical care. Patients have faced a great difficulty in getting access to hospitals. The primary reason being overcrowding of hospitals but another significant reason is lack of information about the hospitals among the general populous. This problem has serious consequences not only on COVID patients but also on other non-COVID patients who are required to take extra precautions in this pandemic as their current health puts them at higher risk (Ardabili, 2020). The non-COVID patients are also finding serious difficulties in getting treatment due to lack of proper information about hospitals and details regarding their current status (Ardabili, 2020).
To get the precise information about hospitals like the availability of beds, availability of ventilators and any other such details about hospitals, people generally follow the traditional process of question-answers where they ask from their friends, acquaintances and other people who might have used the facilities of the particular hospital or may know about the hospital. But this process may take a lot of time and it is not always feasible to ask people. Now-a-days, people rely on online reviews of the hospitals posted by the patients and other stakeholders on various blogs and social networking websites which are easily accessible on internet (Kumar et al., 2018). Patients share their opinions, suggestions and other thoughts on various review sites which may be either favourable or unfavourable. However, these reviews are largely in unstructured form containing sarcasm, language slangs etc. which makes it difficult to interpret them and draw a meaningful conclusion from them. Also, it takes a lot of time to read all the reviews.
Thus, the manual way of filtering out reviews associated with a hospital's status and condition is not scalable and also has reliability issues. Hence, it becomes necessary to automate the process of categorizing the sentiment from reviews or posts by analysing the text using Natural Language Processing (NLP) techniques along with various computational techniques (Hussein, 2018).