A topic-agnostic approach for identifying fake news pages

Sonia Castelo, Aécio Santos, Thais Almeida, Kien Pham, Juliana Freire, Anas Elghafari, Eduardo Nakamura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Fake news and misinformation have been increasingly used to manipulate popular opinion and influence political processes. To better understand fake news, how they are propagated, and how to counter their effect, it is necessary to first identify them. Recently, approaches have been proposed to automatically classify articles as fake based on their content. An important challenge for these approaches comes from the dynamic nature of news: as new political events are covered, topics and discourse constantly change and thus, a classifier trained using content from articles published at a given time is likely to become ineffective in the future. To address this challenge, we propose a topic-agnostic (TAG) classification strategy that uses linguistic and web-markup features to identify fake news pages. We report experimental results using multiple data sets which show that our approach attains high accuracy in the identification of fake news, even as topics evolve over time.

Original languageEnglish (US)
Title of host publicationThe Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019
PublisherAssociation for Computing Machinery, Inc
Pages975-980
Number of pages6
ISBN (Electronic)9781450366755
DOIs
StatePublished - May 13 2019
Event2019 World Wide Web Conference, WWW 2019 - San Francisco, United States
Duration: May 13 2019May 17 2019

Publication series

NameThe Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019

Conference

Conference2019 World Wide Web Conference, WWW 2019
CountryUnited States
CitySan Francisco
Period5/13/195/17/19

Fingerprint

Linguistics
Classifiers

Keywords

  • Classification
  • Fake News Detection
  • Misinformation
  • Online News

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software

Cite this

Castelo, S., Santos, A., Almeida, T., Pham, K., Freire, J., Elghafari, A., & Nakamura, E. (2019). A topic-agnostic approach for identifying fake news pages. In The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019 (pp. 975-980). (The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3308560.3316739

A topic-agnostic approach for identifying fake news pages. / Castelo, Sonia; Santos, Aécio; Almeida, Thais; Pham, Kien; Freire, Juliana; Elghafari, Anas; Nakamura, Eduardo.

The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. p. 975-980 (The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Castelo, S, Santos, A, Almeida, T, Pham, K, Freire, J, Elghafari, A & Nakamura, E 2019, A topic-agnostic approach for identifying fake news pages. in The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019. The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019, Association for Computing Machinery, Inc, pp. 975-980, 2019 World Wide Web Conference, WWW 2019, San Francisco, United States, 5/13/19. https://doi.org/10.1145/3308560.3316739
Castelo S, Santos A, Almeida T, Pham K, Freire J, Elghafari A et al. A topic-agnostic approach for identifying fake news pages. In The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc. 2019. p. 975-980. (The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019). https://doi.org/10.1145/3308560.3316739
Castelo, Sonia ; Santos, Aécio ; Almeida, Thais ; Pham, Kien ; Freire, Juliana ; Elghafari, Anas ; Nakamura, Eduardo. / A topic-agnostic approach for identifying fake news pages. The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. pp. 975-980 (The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019).
@inproceedings{febde2d6741945d7a301c80d9862ebff,
title = "A topic-agnostic approach for identifying fake news pages",
abstract = "Fake news and misinformation have been increasingly used to manipulate popular opinion and influence political processes. To better understand fake news, how they are propagated, and how to counter their effect, it is necessary to first identify them. Recently, approaches have been proposed to automatically classify articles as fake based on their content. An important challenge for these approaches comes from the dynamic nature of news: as new political events are covered, topics and discourse constantly change and thus, a classifier trained using content from articles published at a given time is likely to become ineffective in the future. To address this challenge, we propose a topic-agnostic (TAG) classification strategy that uses linguistic and web-markup features to identify fake news pages. We report experimental results using multiple data sets which show that our approach attains high accuracy in the identification of fake news, even as topics evolve over time.",
keywords = "Classification, Fake News Detection, Misinformation, Online News",
author = "Sonia Castelo and A{\'e}cio Santos and Thais Almeida and Kien Pham and Juliana Freire and Anas Elghafari and Eduardo Nakamura",
year = "2019",
month = "5",
day = "13",
doi = "10.1145/3308560.3316739",
language = "English (US)",
series = "The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019",
publisher = "Association for Computing Machinery, Inc",
pages = "975--980",
booktitle = "The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019",

}

TY - GEN

T1 - A topic-agnostic approach for identifying fake news pages

AU - Castelo, Sonia

AU - Santos, Aécio

AU - Almeida, Thais

AU - Pham, Kien

AU - Freire, Juliana

AU - Elghafari, Anas

AU - Nakamura, Eduardo

PY - 2019/5/13

Y1 - 2019/5/13

N2 - Fake news and misinformation have been increasingly used to manipulate popular opinion and influence political processes. To better understand fake news, how they are propagated, and how to counter their effect, it is necessary to first identify them. Recently, approaches have been proposed to automatically classify articles as fake based on their content. An important challenge for these approaches comes from the dynamic nature of news: as new political events are covered, topics and discourse constantly change and thus, a classifier trained using content from articles published at a given time is likely to become ineffective in the future. To address this challenge, we propose a topic-agnostic (TAG) classification strategy that uses linguistic and web-markup features to identify fake news pages. We report experimental results using multiple data sets which show that our approach attains high accuracy in the identification of fake news, even as topics evolve over time.

AB - Fake news and misinformation have been increasingly used to manipulate popular opinion and influence political processes. To better understand fake news, how they are propagated, and how to counter their effect, it is necessary to first identify them. Recently, approaches have been proposed to automatically classify articles as fake based on their content. An important challenge for these approaches comes from the dynamic nature of news: as new political events are covered, topics and discourse constantly change and thus, a classifier trained using content from articles published at a given time is likely to become ineffective in the future. To address this challenge, we propose a topic-agnostic (TAG) classification strategy that uses linguistic and web-markup features to identify fake news pages. We report experimental results using multiple data sets which show that our approach attains high accuracy in the identification of fake news, even as topics evolve over time.

KW - Classification

KW - Fake News Detection

KW - Misinformation

KW - Online News

UR - http://www.scopus.com/inward/record.url?scp=85066884280&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066884280&partnerID=8YFLogxK

U2 - 10.1145/3308560.3316739

DO - 10.1145/3308560.3316739

M3 - Conference contribution

AN - SCOPUS:85066884280

T3 - The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019

SP - 975

EP - 980

BT - The Web Conference 2019 - Companion of the World Wide Web Conference, WWW 2019

PB - Association for Computing Machinery, Inc

ER -