Factuality Checking in News Headlines with Eye Tracking

Christian Hansen; Casper Hansen; Jakob Grue Simonsen; Birger Larsen; Stephen Alstrup; Christina Lioma

doi:10.1145/3397271.3401221

Factuality Checking in News Headlines with Eye Tracking

Christian Hansen, Casper Hansen, Jakob Grue Simonsen, Birger Larsen, Stephen Alstrup, Christina Lioma

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

7 Citationer (Scopus)

Abstract

We study whether it is possible to infer if a news headline is true or false using only the movement of the human eyes when reading news headlines. Our study with 55 participants who are eye-tracked when reading 108 news headlines (72 true, 36 false) shows that false headlines receive statistically significantly less visual attention than true headlines. We further build an ensemble learner that predicts news headline factuality using only eye-tracking measurements. Our model yields a mean AUC of 0.688 and is better at detecting false than true headlines. Through a model analysis, we find that eye-tracking 25 users when reading 3-6 headlines is sufficient for our ensemble learner.

Originalsprog	Engelsk
Titel	Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
Antal sider	4
Forlag	Association for Computing Machinery
Publikationsdato	25 jul. 2020
Sider	2013-2016
ISBN (Elektronisk)	9781450380164
DOI	https://doi.org/10.1145/3397271.3401221
Status	Udgivet - 25 jul. 2020
Begivenhed	43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020 - Virtual, Online, Kina Varighed: 25 jul. 2020 → 30 jul. 2020

Konference

Konference	43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020
Land/Område	Kina
By	Virtual, Online
Periode	25/07/2020 → 30/07/2020
Sponsor	Special Interest Group on Information Retrieval (ACM SIGIR)

Adgang til dokumentet

10.1145/3397271.3401221

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Andre filer og links

http://www.scopus.com/inward/record.url?scp=85090120754&partnerID=8YFLogxK

Falske nyheder fanger ikke
Birger Larsen
17/09/2020
1 element af Mediedækning
Presse/medie
Øjenbevægelser afslører fake news
Birger Larsen
07/09/2020
1 element af Mediedækning
Presse/medie
Studie: Øjet bruger mindre tid på 'fake news'-overskrifter
Birger Larsen
19/08/2020 → 25/08/2020
4 elementer af Mediedækning
Presse/medie

Citationsformater

@inproceedings{00cc2d81b8b14242bc0d09e76b2c7601,

title = "Factuality Checking in News Headlines with Eye Tracking",

abstract = "We study whether it is possible to infer if a news headline is true or false using only the movement of the human eyes when reading news headlines. Our study with 55 participants who are eye-tracked when reading 108 news headlines (72 true, 36 false) shows that false headlines receive statistically significantly less visual attention than true headlines. We further build an ensemble learner that predicts news headline factuality using only eye-tracking measurements. Our model yields a mean AUC of 0.688 and is better at detecting false than true headlines. Through a model analysis, we find that eye-tracking 25 users when reading 3-6 headlines is sufficient for our ensemble learner.",

keywords = "eye tracking, factuality checking, fake news",

author = "Christian Hansen and Casper Hansen and Simonsen, {Jakob Grue} and Birger Larsen and Stephen Alstrup and Christina Lioma",

year = "2020",

month = jul,

day = "25",

doi = "10.1145/3397271.3401221",

language = "English",

pages = "2013--2016",

booktitle = "Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval",

publisher = "Association for Computing Machinery",

address = "United States",

note = "43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020 ; Conference date: 25-07-2020 Through 30-07-2020",

}

Hansen, C, Hansen, C, Simonsen, JG, Larsen, B, Alstrup, S & Lioma, C 2020, Factuality Checking in News Headlines with Eye Tracking. i Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, s. 2013-2016, 43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020, Virtual, Online, Kina, 25/07/2020. https://doi.org/10.1145/3397271.3401221

Factuality Checking in News Headlines with Eye Tracking. / Hansen, Christian; Hansen, Casper; Simonsen, Jakob Grue et al.
Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, 2020. s. 2013-2016.

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Factuality Checking in News Headlines with Eye Tracking

AU - Hansen, Christian

AU - Hansen, Casper

AU - Simonsen, Jakob Grue

AU - Larsen, Birger

AU - Alstrup, Stephen

AU - Lioma, Christina

PY - 2020/7/25

Y1 - 2020/7/25

N2 - We study whether it is possible to infer if a news headline is true or false using only the movement of the human eyes when reading news headlines. Our study with 55 participants who are eye-tracked when reading 108 news headlines (72 true, 36 false) shows that false headlines receive statistically significantly less visual attention than true headlines. We further build an ensemble learner that predicts news headline factuality using only eye-tracking measurements. Our model yields a mean AUC of 0.688 and is better at detecting false than true headlines. Through a model analysis, we find that eye-tracking 25 users when reading 3-6 headlines is sufficient for our ensemble learner.

AB - We study whether it is possible to infer if a news headline is true or false using only the movement of the human eyes when reading news headlines. Our study with 55 participants who are eye-tracked when reading 108 news headlines (72 true, 36 false) shows that false headlines receive statistically significantly less visual attention than true headlines. We further build an ensemble learner that predicts news headline factuality using only eye-tracking measurements. Our model yields a mean AUC of 0.688 and is better at detecting false than true headlines. Through a model analysis, we find that eye-tracking 25 users when reading 3-6 headlines is sufficient for our ensemble learner.

KW - eye tracking

KW - factuality checking

KW - fake news

UR - http://www.scopus.com/inward/record.url?scp=85090120754&partnerID=8YFLogxK

U2 - 10.1145/3397271.3401221

DO - 10.1145/3397271.3401221

M3 - Article in proceeding

AN - SCOPUS:85090120754

SP - 2013

EP - 2016

BT - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

PB - Association for Computing Machinery

T2 - 43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020

Y2 - 25 July 2020 through 30 July 2020

ER -

Factuality Checking in News Headlines with Eye Tracking

Abstract

Konference

Adgang til dokumentet

AUB Link

Andre filer og links

Fingeraftryk

Presse/Medier

Falske nyheder fanger ikke

Øjenbevægelser afslører fake news

Studie: Øjet bruger mindre tid på 'fake news'-overskrifter

Citationsformater