Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
Add to list
  1. Search results
  2. Preventing profiling for ethical fake...

Preventing profiling for ethical fake news detection

Liesbeth Allein (UGent) , Marie-Francine Moens and Domenico Perrotta
(2023) INFORMATION PROCESSING & MANAGEMENT. 60(2).
Author
Organization
Abstract
A news article's online audience provides useful insights about the article's identity. However, fake news classifiers using such information risk relying on profiling. In response to the rising demand for ethical AI, we present a profiling-avoiding algorithm that leverages Twitter users during model optimisation while excluding them when an article's veracity is evaluated. For this, we take inspiration from the social sciences and introduce two objective functions that max-imise correlation between the article and its spreaders, and among those spreaders. We applied our profiling-avoiding algorithm to three popular neural classifiers and obtained results on fake news data discussing a variety of news topics. The positive impact on prediction performance demonstrates the soundness of the proposed objective functions to integrate social context in text-based classifiers. Moreover, statistical visualisation and dimension reduction techniques show that the user-inspired classifiers better discriminate between unseen fake and true news in their latent spaces. Our study serves as a stepping stone to resolve the underexplored issue of profiling-dependent decision-making in user-informed fake news detection.
Keywords
Fake news detection, Ethics, Profiling, Natural language processing, Constrained representation learning

Citation

Please use this url to cite or link to this publication:

MLA
Allein, Liesbeth, et al. “Preventing Profiling for Ethical Fake News Detection.” INFORMATION PROCESSING & MANAGEMENT, vol. 60, no. 2, 2023, doi:10.1016/j.ipm.2022.103206.
APA
Allein, L., Moens, M.-F., & Perrotta, D. (2023). Preventing profiling for ethical fake news detection. INFORMATION PROCESSING & MANAGEMENT, 60(2). https://doi.org/10.1016/j.ipm.2022.103206
Chicago author-date
Allein, Liesbeth, Marie-Francine Moens, and Domenico Perrotta. 2023. “Preventing Profiling for Ethical Fake News Detection.” INFORMATION PROCESSING & MANAGEMENT 60 (2). https://doi.org/10.1016/j.ipm.2022.103206.
Chicago author-date (all authors)
Allein, Liesbeth, Marie-Francine Moens, and Domenico Perrotta. 2023. “Preventing Profiling for Ethical Fake News Detection.” INFORMATION PROCESSING & MANAGEMENT 60 (2). doi:10.1016/j.ipm.2022.103206.
Vancouver
1.
Allein L, Moens M-F, Perrotta D. Preventing profiling for ethical fake news detection. INFORMATION PROCESSING & MANAGEMENT. 2023;60(2).
IEEE
[1]
L. Allein, M.-F. Moens, and D. Perrotta, “Preventing profiling for ethical fake news detection,” INFORMATION PROCESSING & MANAGEMENT, vol. 60, no. 2, 2023.
@article{01K951114MHVM5BARCVTMBTKF3,
  abstract     = {{A news article's online audience provides useful insights about the article's identity. However, fake news classifiers using such information risk relying on profiling. In response to the rising demand for ethical AI, we present a profiling-avoiding algorithm that leverages Twitter users during model optimisation while excluding them when an article's veracity is evaluated. For this, we take inspiration from the social sciences and introduce two objective functions that max-imise correlation between the article and its spreaders, and among those spreaders. We applied our profiling-avoiding algorithm to three popular neural classifiers and obtained results on fake news data discussing a variety of news topics. The positive impact on prediction performance demonstrates the soundness of the proposed objective functions to integrate social context in text-based classifiers. Moreover, statistical visualisation and dimension reduction techniques show that the user-inspired classifiers better discriminate between unseen fake and true news in their latent spaces. Our study serves as a stepping stone to resolve the underexplored issue of profiling-dependent decision-making in user-informed fake news detection.}},
  articleno    = {{103206}},
  author       = {{Allein, Liesbeth and Moens, Marie-Francine and Perrotta, Domenico}},
  issn         = {{0306-4573}},
  journal      = {{INFORMATION PROCESSING & MANAGEMENT}},
  keywords     = {{Fake news detection,Ethics,Profiling,Natural language processing,Constrained representation learning}},
  language     = {{eng}},
  number       = {{2}},
  pages        = {{22}},
  title        = {{Preventing profiling for ethical fake news detection}},
  url          = {{http://doi.org/10.1016/j.ipm.2022.103206}},
  volume       = {{60}},
  year         = {{2023}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: