Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xu, Tianliang, Brown, Eva Maxfield, Dwyer, Dustin, Tomkins, Sabina
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.11743
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913737857826816
author Xu, Tianliang
Brown, Eva Maxfield
Dwyer, Dustin
Tomkins, Sabina
author_facet Xu, Tianliang
Brown, Eva Maxfield
Dwyer, Dustin
Tomkins, Sabina
contents Local governments around the world are making consequential decisions on behalf of their constituents, and these constituents are responding with requests, advice, and assessments of their officials at public meetings. So many small meetings cannot be covered by traditional newsrooms at scale. We propose PUBLICSPEAK, a probabilistic framework which can utilize meeting structure, domain knowledge, and linguistic information to discover public remarks in local government meetings. We then use our approach to inspect the issues raised by constituents in 7 cities across the United States. We evaluate our approach on a novel dataset of local government meetings and find that PUBLICSPEAK improves over state-of-the-art by 10% on average, and by up to 40%.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11743
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PUBLICSPEAK: Hearing the Public with a Probabilistic Framework in Local Government
Xu, Tianliang
Brown, Eva Maxfield
Dwyer, Dustin
Tomkins, Sabina
Artificial Intelligence
Computers and Society
Local governments around the world are making consequential decisions on behalf of their constituents, and these constituents are responding with requests, advice, and assessments of their officials at public meetings. So many small meetings cannot be covered by traditional newsrooms at scale. We propose PUBLICSPEAK, a probabilistic framework which can utilize meeting structure, domain knowledge, and linguistic information to discover public remarks in local government meetings. We then use our approach to inspect the issues raised by constituents in 7 cities across the United States. We evaluate our approach on a novel dataset of local government meetings and find that PUBLICSPEAK improves over state-of-the-art by 10% on average, and by up to 40%.
title PUBLICSPEAK: Hearing the Public with a Probabilistic Framework in Local Government
topic Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2503.11743