skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Explaining Multimodal Deceptive News Prediction Models

Abstract

Social media plays a valuable role in rapid news dissemination, but it also serves as a vehicle to propagate unverified information. For example, news shared on Facebook or Twitter may actually contain disinformation, propaganda, hoaxes, conspiracies, clickbait or satire. This paper presents an in-depth analysis of the behavior of suspicious news classification models including error analysis and prediction confidence. We consider five deep learning architectures that leverage combinations of text, linguistic and image input signals from tweets. The behavior of these models is analyzed across four suspicious news prediction tasks. Our findings include that models leveraging only the text of tweets outperform those leveraging only the image (by 3-13% absolute in F-measure), and that models that combine image and text signals with linguistic cues e.g., biased and subjective language markers can, but do not always, perform even better. Finally, our main contribution is a series of analyses, in which we characterize text and image traits of our classes of suspicious news and analyze patterns of errors made by the various models to inform the design of future deceptive news prediction models.

Authors:
 [1];  [1];  [1];  [1];  [2]
  1. BATTELLE (PACIFIC NW LAB)
  2. WESTERN WASHINGTON UNIVERSITY
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1532355
Report Number(s):
PNNL-SA-135457
DOE Contract Number:  
AC05-76RL01830
Resource Type:
Conference
Resource Relation:
Conference: Proceedings of the Thirteenth International AAAI Conference on Web and Social Media (ICWSM 2019), June 11-14, 2019, Munich, Germany
Country of Publication:
United States
Language:
English
Subject:
deep learning, social media, deception

Citation Formats

Volkova, Svitlana, Ayton, Ellyn M., Arendt, Dustin L., Huang, Zhuanyi, and Hutchinson, Brian J. Explaining Multimodal Deceptive News Prediction Models. United States: N. p., 2019. Web.
Volkova, Svitlana, Ayton, Ellyn M., Arendt, Dustin L., Huang, Zhuanyi, & Hutchinson, Brian J. Explaining Multimodal Deceptive News Prediction Models. United States.
Volkova, Svitlana, Ayton, Ellyn M., Arendt, Dustin L., Huang, Zhuanyi, and Hutchinson, Brian J. Sat . "Explaining Multimodal Deceptive News Prediction Models". United States.
@article{osti_1532355,
title = {Explaining Multimodal Deceptive News Prediction Models},
author = {Volkova, Svitlana and Ayton, Ellyn M. and Arendt, Dustin L. and Huang, Zhuanyi and Hutchinson, Brian J.},
abstractNote = {Social media plays a valuable role in rapid news dissemination, but it also serves as a vehicle to propagate unverified information. For example, news shared on Facebook or Twitter may actually contain disinformation, propaganda, hoaxes, conspiracies, clickbait or satire. This paper presents an in-depth analysis of the behavior of suspicious news classification models including error analysis and prediction confidence. We consider five deep learning architectures that leverage combinations of text, linguistic and image input signals from tweets. The behavior of these models is analyzed across four suspicious news prediction tasks. Our findings include that models leveraging only the text of tweets outperform those leveraging only the image (by 3-13% absolute in F-measure), and that models that combine image and text signals with linguistic cues e.g., biased and subjective language markers can, but do not always, perform even better. Finally, our main contribution is a series of analyses, in which we characterize text and image traits of our classes of suspicious news and analyze patterns of errors made by the various models to inform the design of future deceptive news prediction models.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {7}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: