Exploring thematic coherence in fake news

Martins Samuel Dogo; Deepak Padmanabhan; Anna Jurek-Loughrey

doi:10.1007/978-3-030-65965-3_40

Exploring thematic coherence in fake news

Martins Samuel Dogo^*, Deepak Padmanabhan, Anna Jurek-Loughrey

^*Corresponding author for this work

School of Electronics, Electrical Engineering and Computer Science

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

5 Citations (Scopus)

47 Downloads (Pure)

Abstract

The spread of fake news remains a serious global issue; understanding and curtailing it is paramount. One way of differentiating between deceptive and truthful stories is by analyzing their coherence. This study explores the use of topic models to analyze the coherence of cross-domain news shared online. Experimental results on seven cross-domain datasets demonstrate that fake news shows a greater thematic deviation between its opening sentences and its remainder.

Original language	English
Title of host publication	Proccedings of the workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020
Publisher	Springer Cham
Pages	571-580
ISBN (Electronic)	9783030659653
ISBN (Print)	9783030659646
DOIs	https://doi.org/10.1007/978-3-030-65965-3_40
Publication status	Published - 02 Feb 2021
Event	8th International Workshop on News Recommendation and Analytics (INRA 2020) - Duration: 14 Sept 2020 → 14 Sept 2020 https://www.ntnu.no/wiki/pages/viewpage.action?pageId=188580623

Publication series

Name	Communications in Computer and Information Science
Publisher	Springer
Volume	1323
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Workshop

Workshop	8th International Workshop on News Recommendation and Analytics (INRA 2020)
Period	14/09/2020 → 14/09/2020
Internet address	https://www.ntnu.no/wiki/pages/viewpage.action?pageId=188580623

Access to Document

10.1007/978-3-030-65965-3_40Licence: CC BY

Exploring thematic coherence in fake news
Copyright 2020 The Authors. This is an open access article published under a Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium, provided the author and source are cited.
Final published version, 577 KBLicence: CC BY

Exploring text representations for online misinformation
Dogo, M. S. (Author), Jurek-Loughrey, A. (Supervisor) & Padmanabhan, D. (Supervisor), Jul 2023
Student thesis: Masters Thesis › Master of Philosophy

File

Cite this

Dogo, M. S., Padmanabhan, D., & Jurek-Loughrey, A. (2021). Exploring thematic coherence in fake news. In Proccedings of the workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020 (pp. 571-580). (Communications in Computer and Information Science; Vol. 1323). Springer Cham. https://doi.org/10.1007/978-3-030-65965-3_40

Dogo, Martins Samuel ; Padmanabhan, Deepak ; Jurek-Loughrey, Anna. / Exploring thematic coherence in fake news. Proccedings of the workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020. Springer Cham, 2021. pp. 571-580 (Communications in Computer and Information Science).

@inproceedings{0bdb99aaea1149e7b5cc7e9b16a4aafe,

title = "Exploring thematic coherence in fake news",

abstract = "The spread of fake news remains a serious global issue; understanding and curtailing it is paramount. One way of differentiating between deceptive and truthful stories is by analyzing their coherence. This study explores the use of topic models to analyze the coherence of cross-domain news shared online. Experimental results on seven cross-domain datasets demonstrate that fake news shows a greater thematic deviation between its opening sentences and its remainder.",

author = "Dogo, {Martins Samuel} and Deepak Padmanabhan and Anna Jurek-Loughrey",

year = "2021",

month = feb,

day = "2",

doi = "10.1007/978-3-030-65965-3_40",

language = "English",

isbn = "9783030659646",

series = "Communications in Computer and Information Science",

publisher = "Springer Cham",

pages = "571--580",

booktitle = "Proccedings of the workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020",

note = "8th International Workshop on News Recommendation and Analytics (INRA 2020) ; Conference date: 14-09-2020 Through 14-09-2020",

url = "https://www.ntnu.no/wiki/pages/viewpage.action?pageId=188580623",

}

Dogo, MS, Padmanabhan, D & Jurek-Loughrey, A 2021, Exploring thematic coherence in fake news. in Proccedings of the workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020. Communications in Computer and Information Science, vol. 1323, Springer Cham, pp. 571-580, 8th International Workshop on News Recommendation and Analytics (INRA 2020), 14/09/2020. https://doi.org/10.1007/978-3-030-65965-3_40

Exploring thematic coherence in fake news. / Dogo, Martins Samuel; Padmanabhan, Deepak ; Jurek-Loughrey, Anna.
Proccedings of the workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020. Springer Cham, 2021. p. 571-580 (Communications in Computer and Information Science; Vol. 1323).

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

TY - GEN

T1 - Exploring thematic coherence in fake news

AU - Dogo, Martins Samuel

AU - Padmanabhan, Deepak

AU - Jurek-Loughrey, Anna

PY - 2021/2/2

Y1 - 2021/2/2

N2 - The spread of fake news remains a serious global issue; understanding and curtailing it is paramount. One way of differentiating between deceptive and truthful stories is by analyzing their coherence. This study explores the use of topic models to analyze the coherence of cross-domain news shared online. Experimental results on seven cross-domain datasets demonstrate that fake news shows a greater thematic deviation between its opening sentences and its remainder.

AB - The spread of fake news remains a serious global issue; understanding and curtailing it is paramount. One way of differentiating between deceptive and truthful stories is by analyzing their coherence. This study explores the use of topic models to analyze the coherence of cross-domain news shared online. Experimental results on seven cross-domain datasets demonstrate that fake news shows a greater thematic deviation between its opening sentences and its remainder.

U2 - 10.1007/978-3-030-65965-3_40

DO - 10.1007/978-3-030-65965-3_40

M3 - Conference contribution

SN - 9783030659646

T3 - Communications in Computer and Information Science

SP - 571

EP - 580

BT - Proccedings of the workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020

PB - Springer Cham

T2 - 8th International Workshop on News Recommendation and Analytics (INRA 2020)

Y2 - 14 September 2020 through 14 September 2020

ER -

Dogo MS, Padmanabhan D , Jurek-Loughrey A. Exploring thematic coherence in fake news. In Proccedings of the workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020. Springer Cham. 2021. p. 571-580. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-65965-3_40

Exploring thematic coherence in fake news

Abstract

Publication series

Workshop

Access to Document

Fingerprint

Student theses

Exploring text representations for online misinformation

Cite this