Predicting the leading political ideology of YouTube channels using acoustic, textual, and metadata information

Yoan Dinkov, Ahmed Ali, Ivan Koychev, Preslav Nakov

Research output: Contribution to journalConference article

Abstract

We address the problem of predicting the leading political ideology, i.e., left-center-right bias, for YouTube channels of news media. Previous work on the problem has focused exclusively on text and on analysis of the language used, topics discussed, sentiment, and the like. In contrast, here we study videos, which yields an interesting multimodal setup. Starting with gold annotations about the leading political ideology of major world news media from Media Bias/Fact Check, we searched on YouTube to find their corresponding channels, and we downloaded a recent sample of videos from each channel. We crawled more than 1,000 YouTube hours along with the corresponding subtitles and metadata, thus producing a new multimodal dataset. We further developed a multimodal deep-learning architecture for the task. Our analysis shows that the use of acoustic signal helped to improve bias detection by more than 6% absolute over using text and metadata only. We release the dataset to the research community, hoping to help advance the field of multi-modal political bias detection.

Original languageEnglish
Pages (from-to)501-505
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2019-September
DOIs
Publication statusPublished - 1 Jan 2019
Event20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, INTERSPEECH 2019 - Graz, Austria
Duration: 15 Sep 201919 Sep 2019

Fingerprint

Metadata
Acoustics
Gold
Annotation
YouTube
Political Ideology
Text
Deep learning
News Media

Keywords

  • Bias detection
  • Political ideology
  • Propaganda

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Cite this

@article{0c064ab7b6e54f9e9790c86850bfe2b3,
title = "Predicting the leading political ideology of YouTube channels using acoustic, textual, and metadata information",
abstract = "We address the problem of predicting the leading political ideology, i.e., left-center-right bias, for YouTube channels of news media. Previous work on the problem has focused exclusively on text and on analysis of the language used, topics discussed, sentiment, and the like. In contrast, here we study videos, which yields an interesting multimodal setup. Starting with gold annotations about the leading political ideology of major world news media from Media Bias/Fact Check, we searched on YouTube to find their corresponding channels, and we downloaded a recent sample of videos from each channel. We crawled more than 1,000 YouTube hours along with the corresponding subtitles and metadata, thus producing a new multimodal dataset. We further developed a multimodal deep-learning architecture for the task. Our analysis shows that the use of acoustic signal helped to improve bias detection by more than 6{\%} absolute over using text and metadata only. We release the dataset to the research community, hoping to help advance the field of multi-modal political bias detection.",
keywords = "Bias detection, Political ideology, Propaganda",
author = "Yoan Dinkov and Ahmed Ali and Ivan Koychev and Preslav Nakov",
year = "2019",
month = "1",
day = "1",
doi = "10.21437/Interspeech.2019-2965",
language = "English",
volume = "2019-September",
pages = "501--505",
journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
issn = "2308-457X",

}

TY - JOUR

T1 - Predicting the leading political ideology of YouTube channels using acoustic, textual, and metadata information

AU - Dinkov, Yoan

AU - Ali, Ahmed

AU - Koychev, Ivan

AU - Nakov, Preslav

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We address the problem of predicting the leading political ideology, i.e., left-center-right bias, for YouTube channels of news media. Previous work on the problem has focused exclusively on text and on analysis of the language used, topics discussed, sentiment, and the like. In contrast, here we study videos, which yields an interesting multimodal setup. Starting with gold annotations about the leading political ideology of major world news media from Media Bias/Fact Check, we searched on YouTube to find their corresponding channels, and we downloaded a recent sample of videos from each channel. We crawled more than 1,000 YouTube hours along with the corresponding subtitles and metadata, thus producing a new multimodal dataset. We further developed a multimodal deep-learning architecture for the task. Our analysis shows that the use of acoustic signal helped to improve bias detection by more than 6% absolute over using text and metadata only. We release the dataset to the research community, hoping to help advance the field of multi-modal political bias detection.

AB - We address the problem of predicting the leading political ideology, i.e., left-center-right bias, for YouTube channels of news media. Previous work on the problem has focused exclusively on text and on analysis of the language used, topics discussed, sentiment, and the like. In contrast, here we study videos, which yields an interesting multimodal setup. Starting with gold annotations about the leading political ideology of major world news media from Media Bias/Fact Check, we searched on YouTube to find their corresponding channels, and we downloaded a recent sample of videos from each channel. We crawled more than 1,000 YouTube hours along with the corresponding subtitles and metadata, thus producing a new multimodal dataset. We further developed a multimodal deep-learning architecture for the task. Our analysis shows that the use of acoustic signal helped to improve bias detection by more than 6% absolute over using text and metadata only. We release the dataset to the research community, hoping to help advance the field of multi-modal political bias detection.

KW - Bias detection

KW - Political ideology

KW - Propaganda

UR - http://www.scopus.com/inward/record.url?scp=85074689395&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074689395&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2019-2965

DO - 10.21437/Interspeech.2019-2965

M3 - Conference article

AN - SCOPUS:85074689395

VL - 2019-September

SP - 501

EP - 505

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SN - 2308-457X

ER -