Modelling the Effect of Large Language Model Agents on Online Decision-Making

The School of EECS is hosting the following PhD Progress Review 3 Seminar:

Modelling the Effect of Large Language Model Agents on Online Decision-Making

Speaker: Shangqian Li

Abstract:The investigation of opinion modelling can be traced back to the last century in the fields of psychology and social science. Later, online opinion modelling became an important topic in the HCI domain. After LLMs were introduced to the public, people found that they could be used in a wide range of areas. Thus, this project aims first to design an innovative user scenario and an LLM application relevant to online opinion formation and decision-making, and then to investigate their influence on human subjects’ opinion changes. We have conducted three studies by creating three unique user scenarios using generative AI. For each study, a user experiment was conducted to test and determine the application’s effect on opinion modelling, followed by adequate quantitative and qualitative analysis. 

Bio: Shangqian Li is a researcher at The University of Queensland specialising in human–computer interaction and online opinion modelling, with a focus on the role of generative AI in decision-making and critical thinking.