Natural language processing analysis of the psychosocial stressors of mental health disorders during the pandemic.

Over the past few years, the COVID-19 pandemic has exerted various impacts on the world, notably concerning mental health. Nevertheless, the precise influence of psychosocial stressors on this mental health crisis remains largely unexplored. In this study, we employ natural language processing to examine chat text from a mental health helpline. The data was obtained from a chat helpline called Safe Hour from the "It Gets Better" project in Chile. This dataset encompass 10,986 conversations between trained professional volunteers from the foundation and platform users from 2018 to 2020. Our analysis shows a significant increase in conversations covering issues of self-image and interpersonal relations, as well as a decrease in performance themes. Also, we observe that conversations involving themes like self-image and emotional crisis played a role in explaining both suicidal behavior and depressive symptoms. However, anxious symptoms can only be explained by emotional crisis themes. These findings shed light on the intricate connections between psychosocial stressors and various mental health aspects in the context of the COVID-19 pandemic.

Citizens at the forefront of the constitutional debate: Voluntary citizen participation determinants and emergent content in Chile.

In the past few decades, constitution-making processes have shifted from being undertakings performed by elites and closed off from the public to ones incorporating democratic mechanisms. Little is known, however, about the determinants of voluntary public participation and how they affect the outcomes of the deliberative process in terms of content and quality. Here, we study the process of constituent involvement in the rewriting of Chile's constitution in 2016. A total of 106, 412 citizens in 8, 113 different local encounters voluntarily congregated in groups of ten or more to collectively determine what social rights should be considered for inclusion in the new constitution, deliberating and then articulating in the written word why should be included. We brought our data to statistical regression models at the municipality level, the results show that the main determinants associated with increasing citizen participation are educational level, engagement in politics, support for the government, and Internet access. In contrast, population density and the share of Evangelical Christians in the general population decrease citizen participation. Then, we further analyze the written arguments for each collectively-selected constitutional rights. The findings suggest that groups from socioeconomically developed municipalities (with higher educational levels and where the main economic activities are more distant from natural resources), on average, deliberate consistently more about themes, concepts, and ideas compared to groups from less developed municipalities. These results provide an empirical ground on the driver factors of voluntary citizen participation and on the benefits and disadvantages of deliberative democracy. Hence, results can inform the organization of new deliberative processes.