Catching Lies in the Act: A Framework for Early Misinformation Detection on Social Media

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

  • Shreya Ghosh
  • Prasenjit Mitra

Research Organisations

External Research Organisations

  • Pennsylvania State University
View graph of relations

Details

Original languageEnglish
Title of host publicationHT`23
Subtitle of host publicationProceedings of the 34th ACM Conference on Hypertext and Social Media
ISBN (electronic)9798400702327
Publication statusPublished - 5 Sept 2023
Event34th ACM Conference on Hypertext and Social Media, HT 2023 - Rome, Italy
Duration: 4 Sept 20238 Sept 2023

Abstract

The proliferation of social media has intensified the necessity for automated misinformation detection. Existing methods often struggle with early detection, as key information is not readily available during the initial dissemination stages. In this paper, we introduce a novel model for early misinformation detection on social media by classifying information propagation paths and leveraging linguistic patterns. Our model incorporates a causal user attribute inference model to label users as potential misinformation propagators or believers. Designed for early detection, the model includes two auxiliary tasks: forecasting the scope of misinformation dissemination and clustering similar nodes (users) based on their attributes outperforming the current state-of-the-art benchmarks.

Keywords

    discourse analysis, Misinformation, social network

ASJC Scopus subject areas

Cite this

Catching Lies in the Act: A Framework for Early Misinformation Detection on Social Media. / Ghosh, Shreya; Mitra, Prasenjit.
HT`23: Proceedings of the 34th ACM Conference on Hypertext and Social Media. 2023. 36.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Ghosh, S & Mitra, P 2023, Catching Lies in the Act: A Framework for Early Misinformation Detection on Social Media. in HT`23: Proceedings of the 34th ACM Conference on Hypertext and Social Media., 36, 34th ACM Conference on Hypertext and Social Media, HT 2023, Rome, Italy, 4 Sept 2023. https://doi.org/10.1145/3603163.3609057
Ghosh, S., & Mitra, P. (2023). Catching Lies in the Act: A Framework for Early Misinformation Detection on Social Media. In HT`23: Proceedings of the 34th ACM Conference on Hypertext and Social Media Article 36 https://doi.org/10.1145/3603163.3609057
Ghosh S, Mitra P. Catching Lies in the Act: A Framework for Early Misinformation Detection on Social Media. In HT`23: Proceedings of the 34th ACM Conference on Hypertext and Social Media. 2023. 36 doi: 10.1145/3603163.3609057
Ghosh, Shreya ; Mitra, Prasenjit. / Catching Lies in the Act : A Framework for Early Misinformation Detection on Social Media. HT`23: Proceedings of the 34th ACM Conference on Hypertext and Social Media. 2023.
Download
@inproceedings{a761b2c3605d43b58173e6f908149e15,
title = "Catching Lies in the Act: A Framework for Early Misinformation Detection on Social Media",
abstract = "The proliferation of social media has intensified the necessity for automated misinformation detection. Existing methods often struggle with early detection, as key information is not readily available during the initial dissemination stages. In this paper, we introduce a novel model for early misinformation detection on social media by classifying information propagation paths and leveraging linguistic patterns. Our model incorporates a causal user attribute inference model to label users as potential misinformation propagators or believers. Designed for early detection, the model includes two auxiliary tasks: forecasting the scope of misinformation dissemination and clustering similar nodes (users) based on their attributes outperforming the current state-of-the-art benchmarks.",
keywords = "discourse analysis, Misinformation, social network",
author = "Shreya Ghosh and Prasenjit Mitra",
note = "Funding Information: This research was partially funded by the Federal Ministry of Education and Research (BMBF), Germany under the project LeibnizK-ILabor with grant No. 01DD20003. ; 34th ACM Conference on Hypertext and Social Media, HT 2023 ; Conference date: 04-09-2023 Through 08-09-2023",
year = "2023",
month = sep,
day = "5",
doi = "10.1145/3603163.3609057",
language = "English",
booktitle = "HT`23",

}

Download

TY - GEN

T1 - Catching Lies in the Act

T2 - 34th ACM Conference on Hypertext and Social Media, HT 2023

AU - Ghosh, Shreya

AU - Mitra, Prasenjit

N1 - Funding Information: This research was partially funded by the Federal Ministry of Education and Research (BMBF), Germany under the project LeibnizK-ILabor with grant No. 01DD20003.

PY - 2023/9/5

Y1 - 2023/9/5

N2 - The proliferation of social media has intensified the necessity for automated misinformation detection. Existing methods often struggle with early detection, as key information is not readily available during the initial dissemination stages. In this paper, we introduce a novel model for early misinformation detection on social media by classifying information propagation paths and leveraging linguistic patterns. Our model incorporates a causal user attribute inference model to label users as potential misinformation propagators or believers. Designed for early detection, the model includes two auxiliary tasks: forecasting the scope of misinformation dissemination and clustering similar nodes (users) based on their attributes outperforming the current state-of-the-art benchmarks.

AB - The proliferation of social media has intensified the necessity for automated misinformation detection. Existing methods often struggle with early detection, as key information is not readily available during the initial dissemination stages. In this paper, we introduce a novel model for early misinformation detection on social media by classifying information propagation paths and leveraging linguistic patterns. Our model incorporates a causal user attribute inference model to label users as potential misinformation propagators or believers. Designed for early detection, the model includes two auxiliary tasks: forecasting the scope of misinformation dissemination and clustering similar nodes (users) based on their attributes outperforming the current state-of-the-art benchmarks.

KW - discourse analysis

KW - Misinformation

KW - social network

UR - http://www.scopus.com/inward/record.url?scp=85174226835&partnerID=8YFLogxK

U2 - 10.1145/3603163.3609057

DO - 10.1145/3603163.3609057

M3 - Conference contribution

AN - SCOPUS:85174226835

BT - HT`23

Y2 - 4 September 2023 through 8 September 2023

ER -