Shedding Light on the Dark Web: Authorship Attribution in Radical Forums
Online users tend to hide their real identities by adopting different names on the Internet. On Facebook or LinkedIn, for example, people usually appear with their real names. On other standard websites, such as forums, people often use nicknames to protect their real identities. Aliases are used wh...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-09-01
|
Series: | Information |
Subjects: | |
Online Access: | https://www.mdpi.com/2078-2489/13/9/435 |
_version_ | 1797486883450650624 |
---|---|
author | Leonardo Ranaldi Federico Ranaldi Francesca Fallucchi Fabio Massimo Zanzotto |
author_facet | Leonardo Ranaldi Federico Ranaldi Francesca Fallucchi Fabio Massimo Zanzotto |
author_sort | Leonardo Ranaldi |
collection | DOAJ |
description | Online users tend to hide their real identities by adopting different names on the Internet. On Facebook or LinkedIn, for example, people usually appear with their real names. On other standard websites, such as forums, people often use nicknames to protect their real identities. Aliases are used when users are trying to protect their anonymity. This can be a challenge to law enforcement trying to identify users who often change nicknames. In unmonitored contexts, such as the dark web, users expect strong identity protection. Thus, without censorship, these users may create parallel social networks where they can engage in potentially malicious activities that could pose security threats. In this paper, we propose a solution to the need to recognize people who anonymize themselves behind nicknames—the authorship attribution (AA) task—in the challenging context of the dark web: specifically, an English-language Islamic forum dedicated to discussions of issues related to the Islamic world and Islam, in which members of radical Islamic groups are present. We provide extensive analysis by testing models based on transformers, styles, and syntactic features. Downstream of the experiments, we show how models that analyze syntax and style perform better than pre-trained universal language models. |
first_indexed | 2024-03-09T23:39:41Z |
format | Article |
id | doaj.art-2816118abdb04aefaafb0f3f25134960 |
institution | Directory Open Access Journal |
issn | 2078-2489 |
language | English |
last_indexed | 2024-03-09T23:39:41Z |
publishDate | 2022-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Information |
spelling | doaj.art-2816118abdb04aefaafb0f3f251349602023-11-23T16:53:30ZengMDPI AGInformation2078-24892022-09-0113943510.3390/info13090435Shedding Light on the Dark Web: Authorship Attribution in Radical ForumsLeonardo Ranaldi0Federico Ranaldi1Francesca Fallucchi2Fabio Massimo Zanzotto3Department of Innovation and Information Engineering, Guglielmo Marconi University, 00193 Rome, ItalyDepartment of Enterprise Engineering, University of Rome Tor Vergata, 00133 Rome, ItalyDepartment of Innovation and Information Engineering, Guglielmo Marconi University, 00193 Rome, ItalyDepartment of Enterprise Engineering, University of Rome Tor Vergata, 00133 Rome, ItalyOnline users tend to hide their real identities by adopting different names on the Internet. On Facebook or LinkedIn, for example, people usually appear with their real names. On other standard websites, such as forums, people often use nicknames to protect their real identities. Aliases are used when users are trying to protect their anonymity. This can be a challenge to law enforcement trying to identify users who often change nicknames. In unmonitored contexts, such as the dark web, users expect strong identity protection. Thus, without censorship, these users may create parallel social networks where they can engage in potentially malicious activities that could pose security threats. In this paper, we propose a solution to the need to recognize people who anonymize themselves behind nicknames—the authorship attribution (AA) task—in the challenging context of the dark web: specifically, an English-language Islamic forum dedicated to discussions of issues related to the Islamic world and Islam, in which members of radical Islamic groups are present. We provide extensive analysis by testing models based on transformers, styles, and syntactic features. Downstream of the experiments, we show how models that analyze syntax and style perform better than pre-trained universal language models.https://www.mdpi.com/2078-2489/13/9/435natural language processingmachine learningdeep learningdark webjihadist forumradicalization |
spellingShingle | Leonardo Ranaldi Federico Ranaldi Francesca Fallucchi Fabio Massimo Zanzotto Shedding Light on the Dark Web: Authorship Attribution in Radical Forums Information natural language processing machine learning deep learning dark web jihadist forum radicalization |
title | Shedding Light on the Dark Web: Authorship Attribution in Radical Forums |
title_full | Shedding Light on the Dark Web: Authorship Attribution in Radical Forums |
title_fullStr | Shedding Light on the Dark Web: Authorship Attribution in Radical Forums |
title_full_unstemmed | Shedding Light on the Dark Web: Authorship Attribution in Radical Forums |
title_short | Shedding Light on the Dark Web: Authorship Attribution in Radical Forums |
title_sort | shedding light on the dark web authorship attribution in radical forums |
topic | natural language processing machine learning deep learning dark web jihadist forum radicalization |
url | https://www.mdpi.com/2078-2489/13/9/435 |
work_keys_str_mv | AT leonardoranaldi sheddinglightonthedarkwebauthorshipattributioninradicalforums AT federicoranaldi sheddinglightonthedarkwebauthorshipattributioninradicalforums AT francescafallucchi sheddinglightonthedarkwebauthorshipattributioninradicalforums AT fabiomassimozanzotto sheddinglightonthedarkwebauthorshipattributioninradicalforums |