Measuring Cynicism and Trust Using Text Data to Predict Information Diffusion, Polarization and Incivility on Digital Platforms [Seed Funding]
Digital technologies offer unlimited opportunities for social and economic interactions. Yet, the increasing digitalization can also have some unintended harmful consequences, such as online fraud, misinformation, polarization and incivility. Emerging computational social science research has demonstrated the added value of large-scale text analyses of digital interactions for understanding these consequences.
Yet, this emerging field has largely overlooked a construct that more traditional (i.e., survey-based) social science research deemed particularly important for abating the negative side-effects of digitalization: cynicism (and its opposite: trust).
The proposed project will 1) use techniques from Natural Language Processing and machine learning to develop a tool that measures Cynicism and Trust (CaT tool) in text data, and 2) apply the CaT tool to better understand information diffusion, polarization, and incivility on social media platforms.
To develop the CaT tool, we will crowdsource ground truth and human-annotated text data and use contextualized text embeddings methods to develop a supervised machine learning classifier algorithm that will quantify the level of cynicism and trust in a text sequence.
We will then demonstrate how the CaT tool can help to understand three phenomena common on social media platforms: information diffusion, polarization, and incivility. We will test whether expressions of cynicism (vs. trust) in a tweet (measured using the CaT tool) lead to more diffusion (i.e., more retweets), more polarization, and higher levels of incivility.
Studying cynicism and trust on digital platforms will help understand the factors associated with harmful consequences of digital technologies, potentially improving citizens’ and societies’ adaptiveness.
Contact
Cross-cutting themes
The Herbert Simon Research Institute for Health, Well-being, and Adaptiveness is a research center devoted to carrying out excellent, state of the art research in order to contribute to healthy and resilient people. We have selected three themes, which involve the collaboration between various Departments and address actual themes in need of both fundamental and applied research.