Leveraging Generative AI to identify narrative evolution, and target audiences in social media

3856 

Contributed Abstract 

Paper 

Richard Takacs (1), Amir Bagherpour (2), Heather Patsolic (3), Marjorie Willner (2), Sieu Tran (2)

(1) N/A, N/A, (2) co-author, N/A, (3) Johns Hopkins University, N/A

Amir Bagherpour  
co-author

Heather Patsolic  
Johns Hopkins University

Marjorie Willner  
co-author

Sieu Tran  
co-author

Richard Takacs  
N/A

Richard Takacs  
N/A

In an era where information is ubiquitous but increasingly unregulated, malicious actors are leveraging the ambiguity of the information environment to provoke specific responses within target audiences via the use of narratives. In public sector applications, the intent of narrative manipulation is often to affect public debate on issues, electoral processes, and policy decisions. To formulate effective responses, policy makers must understand what narratives are being propagated, who is being targeted, and the potential impacts. However, this type of analysis is often complicated by the volume of content and noise in the information environemnt. Leveraging large volumes of data from social media, inputs from geopolitical monitoring systems, and a predictive modeling capability combining LLMs with traditional statistical simulation approaches, we seek to (1) identify key features in specific narratives in social media data, (2) identify shifts in narratives over time, (3) identify potential target audiences of specific narratives, and (4) identify impact to a target audience.

social media|public policy impact|narrative assessment|generative AI|large langauge models|

Section on Text Analysis

Miscellaneous