Tag
The paper proposes an auditable, user-configurable rule-based method for argument selection in deliberative polling, demonstrating through simulations that it achieves competitive performance with opaque learned rankers while enabling greater transparency and personalization.
An interview with Kalle Lyytinen reflecting on his 1985 MISQ article about language theories in information systems, discussing implications for modern AI including large language models and generative AI.
This paper develops a staged robustness analysis framework that connects Structural Equation Modelling (SEM), Ordinary Least Squares (OLS), and Double Machine Learning (DML) for survey-based latent-construct research, demonstrated on a FinTech Digital Customer Intimacy survey model. The framework provides a reusable template for researchers to assess stability of findings across different estimation methods.