Combating Fake News with Transformers: A Comparative Analysis of Stance Detection and Subjectivity Analysis
The widespread use of social networks has brought to the foreground a very important issue, the veracity of the information circulating within them. Many natural language processing methods have been proposed in the past to assess a post’s content with respect to its reliability; however, end-to-end...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-10-01
|
Series: | Information |
Subjects: | |
Online Access: | https://www.mdpi.com/2078-2489/12/10/409 |
_version_ | 1797514295084318720 |
---|---|
author | Panagiotis Kasnesis Lazaros Toumanidis Charalampos Z. Patrikakis |
author_facet | Panagiotis Kasnesis Lazaros Toumanidis Charalampos Z. Patrikakis |
author_sort | Panagiotis Kasnesis |
collection | DOAJ |
description | The widespread use of social networks has brought to the foreground a very important issue, the veracity of the information circulating within them. Many natural language processing methods have been proposed in the past to assess a post’s content with respect to its reliability; however, end-to-end approaches are not comparable in ability to human beings. To overcome this, in this paper, we propose the use of a more modular approach that produces indicators about a post’s subjectivity and the stance provided by the replies it has received to date, letting the user decide whether (s)he trusts or does not trust the provided information. To this end, we fine-tuned state-of-the-art transformer-based language models and compared their performance with previous related work on stance detection and subjectivity analysis. Finally, we discuss the obtained results. |
first_indexed | 2024-03-10T06:29:46Z |
format | Article |
id | doaj.art-61b154d764994853818a0fddea4d5b9a |
institution | Directory Open Access Journal |
issn | 2078-2489 |
language | English |
last_indexed | 2024-03-10T06:29:46Z |
publishDate | 2021-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Information |
spelling | doaj.art-61b154d764994853818a0fddea4d5b9a2023-11-22T18:37:42ZengMDPI AGInformation2078-24892021-10-01121040910.3390/info12100409Combating Fake News with Transformers: A Comparative Analysis of Stance Detection and Subjectivity AnalysisPanagiotis Kasnesis0Lazaros Toumanidis1Charalampos Z. Patrikakis2Department of Electrical and Electronic Engineering, University of West Attica, 12244 Athens, GreeceDepartment of Electrical and Electronic Engineering, University of West Attica, 12244 Athens, GreeceDepartment of Electrical and Electronic Engineering, University of West Attica, 12244 Athens, GreeceThe widespread use of social networks has brought to the foreground a very important issue, the veracity of the information circulating within them. Many natural language processing methods have been proposed in the past to assess a post’s content with respect to its reliability; however, end-to-end approaches are not comparable in ability to human beings. To overcome this, in this paper, we propose the use of a more modular approach that produces indicators about a post’s subjectivity and the stance provided by the replies it has received to date, letting the user decide whether (s)he trusts or does not trust the provided information. To this end, we fine-tuned state-of-the-art transformer-based language models and compared their performance with previous related work on stance detection and subjectivity analysis. Finally, we discuss the obtained results.https://www.mdpi.com/2078-2489/12/10/409deep learningstance detectionsubjectivity analysistransformersnatural language processingsocial media |
spellingShingle | Panagiotis Kasnesis Lazaros Toumanidis Charalampos Z. Patrikakis Combating Fake News with Transformers: A Comparative Analysis of Stance Detection and Subjectivity Analysis Information deep learning stance detection subjectivity analysis transformers natural language processing social media |
title | Combating Fake News with Transformers: A Comparative Analysis of Stance Detection and Subjectivity Analysis |
title_full | Combating Fake News with Transformers: A Comparative Analysis of Stance Detection and Subjectivity Analysis |
title_fullStr | Combating Fake News with Transformers: A Comparative Analysis of Stance Detection and Subjectivity Analysis |
title_full_unstemmed | Combating Fake News with Transformers: A Comparative Analysis of Stance Detection and Subjectivity Analysis |
title_short | Combating Fake News with Transformers: A Comparative Analysis of Stance Detection and Subjectivity Analysis |
title_sort | combating fake news with transformers a comparative analysis of stance detection and subjectivity analysis |
topic | deep learning stance detection subjectivity analysis transformers natural language processing social media |
url | https://www.mdpi.com/2078-2489/12/10/409 |
work_keys_str_mv | AT panagiotiskasnesis combatingfakenewswithtransformersacomparativeanalysisofstancedetectionandsubjectivityanalysis AT lazarostoumanidis combatingfakenewswithtransformersacomparativeanalysisofstancedetectionandsubjectivityanalysis AT charalamposzpatrikakis combatingfakenewswithtransformersacomparativeanalysisofstancedetectionandsubjectivityanalysis |