Monitoring the well-being of vulnerable transit riders using machine learning based sentiment analysis and social media: Lessons from COVID-19

Abstract

Using open-source data, we show that despite significant reductions in global public transit during the COVID-19 pandemic, ∼20% of ridership continues during social distancing measures. Current urban transport data collection methods do not account for the distinct behavioural and psychological experiences of the population. Therefore, little is known about the travel experience of vulnerable citizens that continue to rely on public transit and their concerns over risk, safety and other stressors that could negatively affect their health and well-being. We develop a machine learning approach to augment conventional transport data collection methods by curating a population segmented Twitter dataset representing the travel experiences of ∼120,000 transit riders before and during the pandemic in Metro Vancouver, Canada. Results show a heightened increase in negative sentiments, differentiated by age, gender and ethnicity associated with public transit indicating signs of psychological stress among travellers during the first and second waves of COVID-19. Our results provide empirical evidence of existing inequalities and additional risks faced by citizens using public transit during the pandemic, and can help raise awareness of the differential risks faced by travellers. Our data collection methods can help inform more targeted social-distancing measures, public health announcements, and transit monitoring services during times of transport disruptions and closures.

An overview of urban analytical approaches to combating the Covid-19 pandemic

“…Social media posts from Twitter, Weibo, and other popular platforms have been used in many studies as social sensing sources, often powered by natural language processing and text mining techniques. Researchers have used social media analytics to detect mental health problems, social responses to health intervention policies, needs for healthcare services, and other hidden or manifested public health issues to study the social impact of the pandemic (e.g., Tiwari et al, 2021; Huang et al, 2022; Tran et al, 2023). • Location intelligence data and aggregated trends data.…”

Profiling Social Sentiment in Times of Health Emergencies with Information from Social Networks and Official Statistics

“…Their study is the first to integrate location intelligence with sentiment analysis, regression, and anomaly detection applied to social media messages concerning disasters, covering a wide array of languages. Tran et al [18] track the well-being of vulnerable transit riders during the COVID-19 period by employing machine learning-based sentiment analysis and social media data. Finally, El Barachi et al [19] develop a framework capable of providing real-time insights into the evolution of public opinion.…”

The Role of Social Media In Promoting The Safety Of Women in Indian Cities

“…Tweets sent with the Twitter app include text messages, audio, video, pictures, emoticons, and hashtags. This tweet content may be utilized to spread awareness among the public, enlightening them to the need to take stern action in the event that harassing tweets are sent out to women, and ultimately, punishing such individuals [17]. Twitter and Instagram, two platforms that support hashtags, may be used to disseminate messages throughout the world and encourage women to voice their opinions and sentiments.…”