Beyond Trolling: Fine-Grained Detection of Antisocial Behavior in Social Media During the Pandemic

Antisocial behavior (ASB), including trolling and aggression, undermines constructive discourse and escalates during periods of societal stress, such as the COVID-19 pandemic. This study aimed to examine ASB on social media during the COVID-19 pandemic by leveraging a novel annotated dataset and sta...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrew Asante, Petr Hajek
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/16/3/173
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850090501770838016
author Andrew Asante
Petr Hajek
author_facet Andrew Asante
Petr Hajek
author_sort Andrew Asante
collection DOAJ
description Antisocial behavior (ASB), including trolling and aggression, undermines constructive discourse and escalates during periods of societal stress, such as the COVID-19 pandemic. This study aimed to examine ASB on social media during the COVID-19 pandemic by leveraging a novel annotated dataset and state-of-the-art transformer models for detection and classification of ASB categories. Specifically, this study examined ASB within a gold-standard corpus of tweets collected from Ghana during a 21-day lockdown. Each tweet was meticulously annotated into ASB categories or non-ASB, enabling a comprehensive analysis of online behaviors. We employed three state-of-the-art transformer-based language models (BERT, RoBERTa, and ELECTRA) and compared their performance against traditional machine learning models. The results demonstrate that the transformer-based approaches substantially outperformed the baseline models, achieving a high detection accuracy across both binary and multiclass classification tasks. RoBERTa excelled in binary ASB detection, attaining a 95.59% accuracy and an F1-score of 94.99%, while BERT led in multiclass classification, with a 94.38% accuracy and an F1-score of 93.92%. Trolling emerged as the most prevalent ASB type, reflecting the polarizing nature of online interactions during the lockdown. This study highlights the potential of transformer-based models in detecting diverse online behaviors and emphasizes the societal implications of ASB during crises. The findings provide a foundation for enhancing moderation tools and fostering healthier online environments.
format Article
id doaj-art-879ecf01357e4eb29c2477190d3c46cd
institution DOAJ
issn 2078-2489
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-879ecf01357e4eb29c2477190d3c46cd2025-08-20T02:42:34ZengMDPI AGInformation2078-24892025-02-0116317310.3390/info16030173Beyond Trolling: Fine-Grained Detection of Antisocial Behavior in Social Media During the PandemicAndrew Asante0Petr Hajek1Science and Research Centre, Faculty of Economics and Administration, University of Pardubice, Studentska 84, 53210 Pardubice, Czech RepublicScience and Research Centre, Faculty of Economics and Administration, University of Pardubice, Studentska 84, 53210 Pardubice, Czech RepublicAntisocial behavior (ASB), including trolling and aggression, undermines constructive discourse and escalates during periods of societal stress, such as the COVID-19 pandemic. This study aimed to examine ASB on social media during the COVID-19 pandemic by leveraging a novel annotated dataset and state-of-the-art transformer models for detection and classification of ASB categories. Specifically, this study examined ASB within a gold-standard corpus of tweets collected from Ghana during a 21-day lockdown. Each tweet was meticulously annotated into ASB categories or non-ASB, enabling a comprehensive analysis of online behaviors. We employed three state-of-the-art transformer-based language models (BERT, RoBERTa, and ELECTRA) and compared their performance against traditional machine learning models. The results demonstrate that the transformer-based approaches substantially outperformed the baseline models, achieving a high detection accuracy across both binary and multiclass classification tasks. RoBERTa excelled in binary ASB detection, attaining a 95.59% accuracy and an F1-score of 94.99%, while BERT led in multiclass classification, with a 94.38% accuracy and an F1-score of 93.92%. Trolling emerged as the most prevalent ASB type, reflecting the polarizing nature of online interactions during the lockdown. This study highlights the potential of transformer-based models in detecting diverse online behaviors and emphasizes the societal implications of ASB during crises. The findings provide a foundation for enhancing moderation tools and fostering healthier online environments.https://www.mdpi.com/2078-2489/16/3/173antisocial behaviordetectionlarge language modeltransformer modelCOVID-19multiclass
spellingShingle Andrew Asante
Petr Hajek
Beyond Trolling: Fine-Grained Detection of Antisocial Behavior in Social Media During the Pandemic
Information
antisocial behavior
detection
large language model
transformer model
COVID-19
multiclass
title Beyond Trolling: Fine-Grained Detection of Antisocial Behavior in Social Media During the Pandemic
title_full Beyond Trolling: Fine-Grained Detection of Antisocial Behavior in Social Media During the Pandemic
title_fullStr Beyond Trolling: Fine-Grained Detection of Antisocial Behavior in Social Media During the Pandemic
title_full_unstemmed Beyond Trolling: Fine-Grained Detection of Antisocial Behavior in Social Media During the Pandemic
title_short Beyond Trolling: Fine-Grained Detection of Antisocial Behavior in Social Media During the Pandemic
title_sort beyond trolling fine grained detection of antisocial behavior in social media during the pandemic
topic antisocial behavior
detection
large language model
transformer model
COVID-19
multiclass
url https://www.mdpi.com/2078-2489/16/3/173
work_keys_str_mv AT andrewasante beyondtrollingfinegraineddetectionofantisocialbehaviorinsocialmediaduringthepandemic
AT petrhajek beyondtrollingfinegraineddetectionofantisocialbehaviorinsocialmediaduringthepandemic