Profiling fake news spreaders on Twitter using BERT and Naive Bayes model

Yutong Sun; Hui Ning

doi:10.1117/12.3011766

7 December 2023 Profiling fake news spreaders on Twitter using BERT and Naive Bayes model

Yutong Sun, Hui Ning

Proceedings Volume 12941, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023); 129414P (2023) https://doi.org/10.1117/12.3011766
Event: Third International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 203), 2023, Yinchuan, China

Abstract

This paper studies a method and model used to profile fake news spreaders. The main task is to determine, based on the Twitter text, whether its author is keen to be a purveyor of fake news. It aims to distinguish profiling fake news spreaders on social as the first step to prevent Fake news from spreading among online users. This paper regards this task as a binary task, merging the Twitter information of each author, using the BERT pre-training language model to extract semantic features of English and Spanish Twitter news, and combining the credibility rating features of Twitter information to jointly make predictions. The accuracy of this classification model on the English data set is 0.7400, and the accuracy of the Spanish classification is 0.8150.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yutong Sun and Hui Ning "Profiling fake news spreaders on Twitter using BERT and Naive Bayes model", Proc. SPIE 12941, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023), 129414P (7 December 2023); https://doi.org/10.1117/12.3011766

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available