Detecting Check-Worthy Claims in Political Debates, Speeches, and Interviews Using Audio Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ivanov, Petar, Koychev, Ivan, Hardalov, Momchil, Nakov, Preslav
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913198950580224
author Ivanov, Petar
Koychev, Ivan
Hardalov, Momchil
Nakov, Preslav
author_facet Ivanov, Petar
Koychev, Ivan
Hardalov, Momchil
Nakov, Preslav
contents Developing tools to automatically detect check-worthy claims in political debates and speeches can greatly help moderators of debates, journalists, and fact-checkers. While previous work on this problem has focused exclusively on the text modality, here we explore the utility of the audio modality as an additional input. We create a new multimodal dataset (text and audio in English) containing 48 hours of speech from past political debates in the USA. We then experimentally demonstrate that, in the case of multiple speakers, adding the audio modality yields sizable improvements over using the text modality alone; moreover, an audio-only model could outperform a text-only one for a single speaker. With the aim to enable future research, we make all our data and code publicly available at https://github.com/petar-iv/audio-checkworthiness-detection.
format Preprint
id arxiv_https___arxiv_org_abs_2306_05535
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Detecting Check-Worthy Claims in Political Debates, Speeches, and Interviews Using Audio Data
Ivanov, Petar
Koychev, Ivan
Hardalov, Momchil
Nakov, Preslav
Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
Sound
Audio and Speech Processing
68T50
F.2.2; I.2.7
Developing tools to automatically detect check-worthy claims in political debates and speeches can greatly help moderators of debates, journalists, and fact-checkers. While previous work on this problem has focused exclusively on the text modality, here we explore the utility of the audio modality as an additional input. We create a new multimodal dataset (text and audio in English) containing 48 hours of speech from past political debates in the USA. We then experimentally demonstrate that, in the case of multiple speakers, adding the audio modality yields sizable improvements over using the text modality alone; moreover, an audio-only model could outperform a text-only one for a single speaker. With the aim to enable future research, we make all our data and code publicly available at https://github.com/petar-iv/audio-checkworthiness-detection.
title Detecting Check-Worthy Claims in Political Debates, Speeches, and Interviews Using Audio Data
topic Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
Sound
Audio and Speech Processing
68T50
F.2.2; I.2.7
url https://arxiv.org/abs/2306.05535