Towards Detecting Harmful Agendas in News Articles

Melanie Subbiah; Amrita Bhattacharjee; Yilun Hua; Tharindu Kumarage; Huan Liu; Kathleen McKeown

Towards Detecting Harmful Agendas in News Articles

Melanie Subbiah, Amrita Bhattacharjee, Yilun Hua, Tharindu Kumarage, Huan Liu, Kathleen McKeown

Engineering, Ira A. Fulton Schools of (IAFSE)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

Manipulated news online is a growing problem which necessitates the use of automated systems to curtail its spread. We argue that while misinformation and disinformation detection have been studied, there has been a lack of investment in the important open challenge of detecting harmful agendas in news articles; identifying harmful agendas is critical to flag news campaigns with the greatest potential for real world harm. Moreover, due to real concerns around censorship, harmful agenda detectors must be interpretable to be effective. In this work, we propose this new task and release a dataset, NEWSAGENDAS, of annotated news articles for agenda identification. We show how interpretable systems can be effective on this task and demonstrate that they can perform comparably to black-box models.

Original language	English (US)
Title of host publication	WASSA 2023 - 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop
Editors	Jeremy Barnes, Orphee De Clercq, Roman Klinger
Publisher	Association for Computational Linguistics (ACL)
Pages	110-128
Number of pages	19
ISBN (Electronic)	9781959429876
State	Published - 2023
Event	13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2023 - Toronto, Canada Duration: Jul 14 2023 → …

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)	0736-587X

Conference

Conference	13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2023
Country/Territory	Canada
City	Toronto
Period	7/14/23 → …

ASJC Scopus subject areas

Computer Science Applications
Linguistics and Language
Language and Linguistics

Cite this

Subbiah, M., Bhattacharjee, A., Hua, Y., Kumarage, T., Liu, H., & McKeown, K. (2023). Towards Detecting Harmful Agendas in News Articles. In J. Barnes, O. De Clercq, & R. Klinger (Eds.), WASSA 2023 - 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop (pp. 110-128). (Proceedings of the Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics (ACL).

Towards Detecting Harmful Agendas in News Articles. / Subbiah, Melanie; Bhattacharjee, Amrita; Hua, Yilun et al.
WASSA 2023 - 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop. ed. / Jeremy Barnes; Orphee De Clercq; Roman Klinger. Association for Computational Linguistics (ACL), 2023. p. 110-128 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Subbiah, M, Bhattacharjee, A, Hua, Y, Kumarage, T, Liu, H & McKeown, K 2023, Towards Detecting Harmful Agendas in News Articles. in J Barnes, O De Clercq & R Klinger (eds), WASSA 2023 - 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL), pp. 110-128, 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2023, Toronto, Canada, 7/14/23.

Subbiah M, Bhattacharjee A, Hua Y, Kumarage T, Liu H, McKeown K. Towards Detecting Harmful Agendas in News Articles. In Barnes J, De Clercq O, Klinger R, editors, WASSA 2023 - 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2023. p. 110-128. (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

Subbiah, Melanie ; Bhattacharjee, Amrita ; Hua, Yilun et al. / Towards Detecting Harmful Agendas in News Articles. WASSA 2023 - 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop. editor / Jeremy Barnes ; Orphee De Clercq ; Roman Klinger. Association for Computational Linguistics (ACL), 2023. pp. 110-128 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{dbd9f5028a94446d93e154bbb38aa67c,

title = "Towards Detecting Harmful Agendas in News Articles",

abstract = "Manipulated news online is a growing problem which necessitates the use of automated systems to curtail its spread. We argue that while misinformation and disinformation detection have been studied, there has been a lack of investment in the important open challenge of detecting harmful agendas in news articles; identifying harmful agendas is critical to flag news campaigns with the greatest potential for real world harm. Moreover, due to real concerns around censorship, harmful agenda detectors must be interpretable to be effective. In this work, we propose this new task and release a dataset, NEWSAGENDAS, of annotated news articles for agenda identification. We show how interpretable systems can be effective on this task and demonstrate that they can perform comparably to black-box models.",

author = "Melanie Subbiah and Amrita Bhattacharjee and Yilun Hua and Tharindu Kumarage and Huan Liu and Kathleen McKeown",

note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2023 ; Conference date: 14-07-2023",

year = "2023",

language = "English (US)",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

pages = "110--128",

editor = "Jeremy Barnes and {De Clercq}, Orphee and Roman Klinger",

booktitle = "WASSA 2023 - 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop",

}

TY - GEN

T1 - Towards Detecting Harmful Agendas in News Articles

AU - Subbiah, Melanie

AU - Bhattacharjee, Amrita

AU - Hua, Yilun

AU - Kumarage, Tharindu

AU - Liu, Huan

AU - McKeown, Kathleen

PY - 2023

Y1 - 2023

N2 - Manipulated news online is a growing problem which necessitates the use of automated systems to curtail its spread. We argue that while misinformation and disinformation detection have been studied, there has been a lack of investment in the important open challenge of detecting harmful agendas in news articles; identifying harmful agendas is critical to flag news campaigns with the greatest potential for real world harm. Moreover, due to real concerns around censorship, harmful agenda detectors must be interpretable to be effective. In this work, we propose this new task and release a dataset, NEWSAGENDAS, of annotated news articles for agenda identification. We show how interpretable systems can be effective on this task and demonstrate that they can perform comparably to black-box models.

AB - Manipulated news online is a growing problem which necessitates the use of automated systems to curtail its spread. We argue that while misinformation and disinformation detection have been studied, there has been a lack of investment in the important open challenge of detecting harmful agendas in news articles; identifying harmful agendas is critical to flag news campaigns with the greatest potential for real world harm. Moreover, due to real concerns around censorship, harmful agenda detectors must be interpretable to be effective. In this work, we propose this new task and release a dataset, NEWSAGENDAS, of annotated news articles for agenda identification. We show how interpretable systems can be effective on this task and demonstrate that they can perform comparably to black-box models.

UR - http://www.scopus.com/inward/record.url?scp=85174802412&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85174802412&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85174802412

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 110

EP - 128

BT - WASSA 2023 - 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop

A2 - Barnes, Jeremy

A2 - De Clercq, Orphee

A2 - Klinger, Roman

PB - Association for Computational Linguistics (ACL)

T2 - 13th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2023

Y2 - 14 July 2023

ER -

Towards Detecting Harmful Agendas in News Articles

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this