Learning personalized consumers’ privacy preferences is crucial for firms and policymakers to establish trust and compliance and guides effective policy-making. Existing approaches rely mostly on private information such as proprietary user behavior data, individual-level demographic and socio-economic factors, or explicit user input, which can be invasive, burdensome, and often lack personalization, leading to user dissatisfaction and privacy fatigue. Nowadays, individuals generate and share vast amounts of information about themselves in the public domain, which can provide a valuable multifaceted view of individuals’ behaviors, attitudes, and preferences and has the potential to provide valuable insights into individuals’ privacy preferences. In this study, we propose a novel framework to predict personalized privacy preferences by leveraging a ubiquitous source of public data - social media posts. Combining psychological theory and deep learning algorithms, we learn theory-driven psycho-social traits such as personality, lifestyles, risk preference, economic thinking, etc from social media posts. Interestingly, we find that psycho-social traits from public data provide significantly greater predictive power than private information. Furthermore, multiple interpretability analyses are conducted to explore the underlying mechanisms. Finally, we demonstrate the practical value of our model and show that our framework can help platforms and policymakers forecast the consequences of privacy policies and prevent potential harms such as discrimination. For example, we find policy leading to high privacy risk could potentially lead to a significant decrease in the female user base on a platform due to females’ potential higher sensitivity to online harassment and abuse. By utilizing our tool, platforms can modulate their risk levels and strike a balance to avoid potential discrimination. Overall, our framework provides managerial implications for enhancing tailored consumer privacy control and trust, optimizing platform data management, and informing policymakers about better data privacy regulations
