Sentiment Analysis of Cancer Patients About Their Treatment During the Peak Time of Pandemic COVID-19

Social media has become a valuable tool for users to express their opinion and for researchers to analyze public sentiment more efficiently. People respond much quickly towards any issue on social than any other traditional platform. Observing the patient's opinion on social media about the hospital medical facilities is a new trend that several hospitals are adopting recently in the modern world to improve their heal care facilities. After the pandemic of SARS-CoV-2, it has influenced the health care practices of all the world. Initial investigations indicate that patients with comorbidities are more fragile to this SARS-CoV-2 infection. Medical experts suggested postponing the routine treatment of cancer patients. However, few meta-analyses suggested evidence are not sufficient to hold the claim of the frailty of cancer patients to COVID-19. They were not in favor of shelving the scheduled treatments. On the other hand, some medical experts favored postponing cancer patients' scheduled treatments like chemotherapy, which could be a dangerous decision for cancer patients. We conducted the sentiment analysis of the patients with various comorbidities (diseases like diabetes, obesity, and cancer in which patient has to visit the hospital more often) to understand their point of view whether they were satisfied during the pandemic with their treatment or not? How Covid-19 affected their scheduled appointments. To serve the purpose, we gathered more than 150000 relevant tweets from Twitter (Jan 2020 to April 2020) to analyze the sentiment of cancer patients around the world. Our findings demonstrate a surge in the argument about cancer and its treatment after the outbreak of COVID-19. Most of the tweets are reasonable (52.6%) compared to negative ones (24.3%). We developed polarity and subjectivity distribution to better recognize the positivity/negativity in the sentiment. The results reveal that the polarity range of positive tweets is within the range of 0 to 0.5. That means the tendency in the tweets is not negative (it is above zero) nor so much positive too. It is statistical evidence supporting how natural language processing (NLP) can be used to better understand the patient's behavior in real-time. It may facilitate the medical professionals to make better decisions to organize the routine management of cancer patients.