@inproceedings{diallo2024voter,
title={All We Need is Voter Feedback: a New Paradigm to Realize Politics without Politicians Using AI Models Aligned with Voter Inputs},
author={Diallo, Nour and Alsagheer, Dana and Kamal, Mohammad and Xu, Lei and Lu, Yang and Karanjai, Rabimba and Shi, Weidong},
booktitle={2024 Tenth International Conference on eDemocracy \& eGovernment (ICEDEG)},
pages={1--9},
year={2024},
organization={IEEE}
}Copied to clipboardFull paper available on the publisher's website.
Open via DOI →In democratic societies, the people elect the government and it is expected to represent their interests through various decisions and actions. However, the relationship between voter opinions and the government’s actions is complex, and many factors can delay or even transform the translation process so that the government’s operation does not reflect the voters’ interests. Recent advancements in natural language processing (NLP) and large language models (LLMs) provide a new opportunity to mitigate this challenge. Specifically, we introduce a new framework that leverages LLMs to assess public sentiment and preferences and transform citizen input into actionable policy recommendations and legislative structures. This translation is highly automated and avoids unnecessary human inferences. Compared with current practices, the new framework improves government transparency and reduces policy unpredictability.