ABSTRACT
Due to the Covid19 pandemic, and the restrictions placed in social interactions, there has been an upsurge in the use of social networks, such as Facebook, WhatsApp, Instagram, Telegram, Twitter, and others. As more people turn to the social networks for social interaction, there has been increased occurrences of cyberbullying. Cyberbullying is a type of bullying that occurs through online technology, whereby harmful texts and pictures are shared through social networks. This research project aimed to develop a system that can detect cyberbullying on social networks such as Twitter focusing on the IsiXhosa language. Machine learning algorithms were applied to Twitter feeds in order to detect cyberbullying. The project will help law enforcement to apprehend and prosecute cyberbullies that make threats using isiXhosa. The methodology used incorporated machine learning algorithms to fully implement the cyberbullying detection system. It starts with collecting the data from Twitter using Python, cleaning the data followed by testing the data. The results show that the implementation successfully collected the desired data from Twitter and the data was then pre-processed and prepared to be tested using the different algorithms mentioned in the paper. © 2022 IEEE.
ABSTRACT
BACKGROUND: While hate crimes rose during the COVID-19 pandemic, few studies examined whether this pandemic-time racial discrimination has led to negative health consequences at the population level. OBJECTIVE: We examined whether experienced and perceived racial discrimination were associated with mental or behavioral health outcomes during the pandemic. DESIGN: In October 2020, we conducted a national survey with minorities oversampled that covered respondents' sociodemographic background and health-related information. PARTICIPANTS: A total of 2709 participants responded to the survey (response rate: 4.2%). MAIN MEASURES: The exposure variables included (1) experienced and encountered racial discrimination, (2) experienced racial and ethnic cyberbullying, and (3) perceived racial bias. Mental health outcomes were measured by psychological distress and self-rated happiness. Measures for behavioral health included sleep quality, change in cigarette smoking, and change in alcohol consumption. Weighted logistic regressions were performed to estimate the associations between the exposure variables and the outcomes, controlling for age, gender, race and ethnicity, educational attainment, household income, eligibility to vote, political party, COVID-19 infection, and geographic region. Separate regressions were performed in the six racial and ethnic subgroups: non-Hispanic White, non-Hispanic Black, Hispanic, East Asian, South Asian, and Southeast Asian respondents. KEY RESULTS: Experienced racial discrimination was associated with higher likelihood of psychological distress (adjusted odds ratio [AOR] = 2.18, 95% confidence interval [95% CI]: 1.34-3.55). Experienced racial discrimination (AOR = 2.31, 95% CI: 1.34-3.99) and perceived racial bias (AOR = 1.05, 95% CI: 1.00-1.09) were both associated with increased cigarette smoking. The associations between racial discrimination and mental distress and substance use were most salient among Black, East Asian, South Asian, and Hispanic respondents. CONCLUSIONS: Racial discrimination may be associated with higher likelihood of distress, and cigarette smoking among racial and ethnic minorities. Addressing racial discrimination is important for mitigating negative mental and behavioral health ramifications of the pandemic.