Media narratives play a critical role in echoing, influencing, and reinforcing public opinion. Yet, it is challenging to represent narratives structurally to empower efficient extraction, let alone to understand their dissemination and influence. This project’s objectives are: (1) designing a computational framework with a unified narrative representation, grounded in social psychological theories, (2) gaining deeper insights into how narratives emerge and spread through the lens of argumentation, and (3) providing practical quantitative measures of narrative influence.
Three research thrusts are proposed. First, this project designs a latent generative narrative representation framework based on moral values, with probabilistic modeling of different linguistic phenomena. Second, the shaping and dissemination of narratives are modeled as an argumentation process with group collaborations to maximize their persuasion effects. Third, multi-scale narrative influence measures are constructed using entity-targeted stances automatically extracted from individuals’ content sharing and posting patterns.
Narrative modeling, moral values, framing, narrative influence, group dynamics
AFOSR. Duration: May 1, 2022 - April 30, 2025.