Change Point Detection in Terrorism-Related Online Content Using Deep Learning Derived Indicators
Given the increasing occurrence of deviant activities in online platforms, it is of paramount importance to develop methods and tools that allow in-depth analysis and understanding to then develop effective countermeasures. This work proposes a framework towards detecting statistically significant c...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | Information |
Subjects: | |
Online Access: | https://www.mdpi.com/2078-2489/12/7/274 |
_version_ | 1797526870598615040 |
---|---|
author | Ourania Theodosiadou Kyriaki Pantelidou Nikolaos Bastas Despoina Chatzakou Theodora Tsikrika Stefanos Vrochidis Ioannis Kompatsiaris |
author_facet | Ourania Theodosiadou Kyriaki Pantelidou Nikolaos Bastas Despoina Chatzakou Theodora Tsikrika Stefanos Vrochidis Ioannis Kompatsiaris |
author_sort | Ourania Theodosiadou |
collection | DOAJ |
description | Given the increasing occurrence of deviant activities in online platforms, it is of paramount importance to develop methods and tools that allow in-depth analysis and understanding to then develop effective countermeasures. This work proposes a framework towards detecting statistically significant change points in terrorism-related time series, which may indicate the occurrence of events to be paid attention to. These change points may reflect changes in the attitude towards and/or engagement with terrorism-related activities and events, possibly signifying, for instance, an escalation in the radicalization process. In particular, the proposed framework involves: (i) classification of online textual data as terrorism- and hate speech-related, which can be considered as indicators of a potential criminal or terrorist activity; and (ii) change point analysis in the time series generated by these data. The use of change point detection (CPD) algorithms in the produced time series of the aforementioned indicators—either in a univariate or two-dimensional case—can lead to the estimation of statistically significant changes in their structural behavior at certain time locations. To evaluate the proposed framework, we apply it on a publicly available dataset related to jihadist forums. Finally, topic detection on the estimated change points is implemented to further assess its effectiveness. |
first_indexed | 2024-03-10T09:36:28Z |
format | Article |
id | doaj.art-98d4dd88918b4b2c8d65444f8c1e638d |
institution | Directory Open Access Journal |
issn | 2078-2489 |
language | English |
last_indexed | 2024-03-10T09:36:28Z |
publishDate | 2021-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Information |
spelling | doaj.art-98d4dd88918b4b2c8d65444f8c1e638d2023-11-22T04:03:49ZengMDPI AGInformation2078-24892021-07-0112727410.3390/info12070274Change Point Detection in Terrorism-Related Online Content Using Deep Learning Derived IndicatorsOurania Theodosiadou0Kyriaki Pantelidou1Nikolaos Bastas2Despoina Chatzakou3Theodora Tsikrika4Stefanos Vrochidis5Ioannis Kompatsiaris6Centre for Research and Technology Hellas, Information Technologies Institute, 57001 Thessaloniki, GreeceCentre for Research and Technology Hellas, Information Technologies Institute, 57001 Thessaloniki, GreeceCentre for Research and Technology Hellas, Information Technologies Institute, 57001 Thessaloniki, GreeceCentre for Research and Technology Hellas, Information Technologies Institute, 57001 Thessaloniki, GreeceCentre for Research and Technology Hellas, Information Technologies Institute, 57001 Thessaloniki, GreeceCentre for Research and Technology Hellas, Information Technologies Institute, 57001 Thessaloniki, GreeceCentre for Research and Technology Hellas, Information Technologies Institute, 57001 Thessaloniki, GreeceGiven the increasing occurrence of deviant activities in online platforms, it is of paramount importance to develop methods and tools that allow in-depth analysis and understanding to then develop effective countermeasures. This work proposes a framework towards detecting statistically significant change points in terrorism-related time series, which may indicate the occurrence of events to be paid attention to. These change points may reflect changes in the attitude towards and/or engagement with terrorism-related activities and events, possibly signifying, for instance, an escalation in the radicalization process. In particular, the proposed framework involves: (i) classification of online textual data as terrorism- and hate speech-related, which can be considered as indicators of a potential criminal or terrorist activity; and (ii) change point analysis in the time series generated by these data. The use of change point detection (CPD) algorithms in the produced time series of the aforementioned indicators—either in a univariate or two-dimensional case—can lead to the estimation of statistically significant changes in their structural behavior at certain time locations. To evaluate the proposed framework, we apply it on a publicly available dataset related to jihadist forums. Finally, topic detection on the estimated change points is implemented to further assess its effectiveness.https://www.mdpi.com/2078-2489/12/7/274change point detectionterrorismhate speechonline contenttopic detection |
spellingShingle | Ourania Theodosiadou Kyriaki Pantelidou Nikolaos Bastas Despoina Chatzakou Theodora Tsikrika Stefanos Vrochidis Ioannis Kompatsiaris Change Point Detection in Terrorism-Related Online Content Using Deep Learning Derived Indicators Information change point detection terrorism hate speech online content topic detection |
title | Change Point Detection in Terrorism-Related Online Content Using Deep Learning Derived Indicators |
title_full | Change Point Detection in Terrorism-Related Online Content Using Deep Learning Derived Indicators |
title_fullStr | Change Point Detection in Terrorism-Related Online Content Using Deep Learning Derived Indicators |
title_full_unstemmed | Change Point Detection in Terrorism-Related Online Content Using Deep Learning Derived Indicators |
title_short | Change Point Detection in Terrorism-Related Online Content Using Deep Learning Derived Indicators |
title_sort | change point detection in terrorism related online content using deep learning derived indicators |
topic | change point detection terrorism hate speech online content topic detection |
url | https://www.mdpi.com/2078-2489/12/7/274 |
work_keys_str_mv | AT ouraniatheodosiadou changepointdetectioninterrorismrelatedonlinecontentusingdeeplearningderivedindicators AT kyriakipantelidou changepointdetectioninterrorismrelatedonlinecontentusingdeeplearningderivedindicators AT nikolaosbastas changepointdetectioninterrorismrelatedonlinecontentusingdeeplearningderivedindicators AT despoinachatzakou changepointdetectioninterrorismrelatedonlinecontentusingdeeplearningderivedindicators AT theodoratsikrika changepointdetectioninterrorismrelatedonlinecontentusingdeeplearningderivedindicators AT stefanosvrochidis changepointdetectioninterrorismrelatedonlinecontentusingdeeplearningderivedindicators AT ioanniskompatsiaris changepointdetectioninterrorismrelatedonlinecontentusingdeeplearningderivedindicators |