Sentiment Analysis of Stress Among the Students Amidst the Covid Pandemic Using Global Tweets

Covid-19 pandemic has affected the lives of people across the globe. People belonging to all the sectors of the society have faced a lot of challenges. Strict measures like lockdown and social distancing have been imposed several times by governments throughout the world. Universities had to incorporate the online method of teaching instead of the regular offline classes to implement social distancing. Online classes were beneficial to most of the students;at the same time, there were many difficulties faced by the students due to lack of facilities to attend classes online. Students faced a lot of challenges, and a sense of anxiety was prevalent during the uncertain times of the pandemic. This research article analyzes the stress among students considering the tweets across the globe related to students stress. The algorithms considered for classification of tweets as positive or negative are support vector machine (SVM), bidirectional encoder representation from transformers (BERT), and long short-term memory (LSTM). The accuracy of the abovementioned algorithms is compared. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Depression, Perceived Stress and Socio-demographic Correlates among General Population during COVID-19 Pandemic: A Cross-sectional Survey from Southern India

Introduction: The Coronavirus Disease 2019 (COVID-19) pandemic and its socio-economic consequences have had a significant impact on mental health. A quantifiable data regarding increase of mental health problems as a result of the pandemic is required to take necessary steps in tackling the issue. Aim: To estimate the prevalence of depression, perceived stress and its socio-demographic correlates among general population of South India during COVID-19. Materials and Methods: This cross-sectional survey conducted from 25th August 2021 to 25th October 2021 among the general population of South India during COVID-19. A total of 600 subjects were enrolled into the study. Study subjects included people of either sex between 20-50 years of age who were able to read and understand English and with access to internet. Subjects responded to a questionnaire packet of Patient Health Questionnaire-9 (PHQ-9), Perceived Stress Scale 10 (PSS-10) and a proforma for socio-demographic data. Data was analyzed using GNU PSPP version 1. One-way Analysis of Variance (ANOVA) and independent t test were used to assess associations. A value of p-value<0.05 was considered to be statistically significant. Pearson’s correlation coefficient was used to determine correlation. Results: Of the 600 subjects who were enrolled into the study, 26.7%, 15.7%, 9.3% and 7.2% had mild, moderate, moderately severe and severe depression respectively. About 62.7% had moderate and 17.5% had high perceived stress. Whereas, 28.7% had death wishes or thoughts to hurt themselves. Females (PHQ-9: p-value=0.006;PSS-10:p-value<0.001), 20-29 age group (PHQ-9: p-value <0.001;PSS-10: p-value <0.001), students (PHQ-9: p-value <0.001;PSS-10: p-value <0.001), those who were unmarried (PHQ-9: p-value <0.001;PSS-10: p-value< 0.001), living with parents (PHQ-9: p-value <0.001;PSS-10: p-value <0.001), those who had a loss of income (PHQ-9: p-value <0.001;PSS-10: p-value=0.018) or job (PHQ-9: p-value<0.001;PSS-10: p-value<0.001) in the past 1 year, those with a history of psychiatry disorder (PHQ-9: p-value<0.001;PSS-10: p-value<0.001) had a significantly higher score in both depression and perceived stress. Correlation analysis showed a significant correlation between depression and perceived stress scores (r=0.691). Conclusion: This study showed a high prevalence of depression and perceived stress and shows the need for strengthening mental health services to address the challenge.

Real-World Crizanlizumab Treatment Patterns of Patients with Sickle Cell Disease

Background: Sickle cell disease (SCD) is an inherited blood disorder characterized by vaso-occlusive crises (VOCs). Crizanlizumab infusion was FDA approved in 2019 to reduce VOCs in patients with SCD ≥16 years old. There is little real-world evidence (RWE) regarding crizanlizumab use. Objective: To describe real-world crizanlizumab utilization. Methods: Using IQVIA’s US-based Longitudinal Pharmacy and Medical Claims Databases, patients with an SCD diagnosis between 01-November-2018 and 30-April-2021, ≥1 crizanlizumab claim (index date=first crizanlizumab claim) between 01-November-2019 and 31-January-2021, aged ≥16-years at index, ≥12-months of pre-index, and ≥6-months of post-index data were identified. Crizanlizumab treatment patterns were characterized by doses received, gap-days between doses (days between end of days-supply of one dose to the next administration), discontinuation (≥60-day gap), days on therapy prior to discontinuation, and restarts. Results: In total 262 patients were included. Of these patients, 235(87%) received dose #2, 204(78%) received dose #3, and 174(66%) received ≥4 doses with a median(interquartile range [IQR]) of 125(43-180) days on therapy prior to discontinuation. In the 6-months post-index, 150(57%) patients discontinued crizanlizumab. Of those patients who discontinued crizanlizumab, 46(31%) restarted. Among the 112 patients that did not discontinue, the median(IQR) gap-days between doses 1&2=2(1-15) days, between doses 2&3=1(1-7) days, between doses 3&4=1(1-5) days, and between doses 4&5=1(1-6) days. At the end of the 6-months of follow-up, 88 patients (34% of all patients) appeared to be on crizanlizumab. Conclusions: This RWE suggests that 66% of patients who receive crizanlizumab receive ≥4 doses within 6-months, patients receiving multiple doses appear to have a reduction in gap-days with each subsequent dose, and that of those who discontinue treatment, 31% restart crizanlizumab within 6-months post-index. Due to the nature of claims data, the reasons for discontinuation or gaps between doses are unknown. The impact of COVID-19 restrictions or other access barriers on crizanlizumab use is also unknown.

Sentiment Analysis On Covid-19 Related Social Distancing Across The Globe Using Twitter Data

Covid 19 pandemic has devastated the lives of several people across the globe. Social distancing is considered a major preventive measure to stop the spread of Covid 19. The practice of social distancing has caused a sense of loneliness and mental health problems in society. The aim of this study is to consider global tweet data with social distancing keywords for analyzing the sentiments behind them. Classification of tweets as positive or negative is carried out using Support Vector Machine and Logistic Regression. © The Electrochemical Society