Leveraging Natural Language Processing to Analyse the Temporal Behavior of Extremists on Social Media

Abstract

Aiming at achieving sustainability and quality of life for citizens, future smart cities adopt a data-centric approach to decision making in which assets, people, and events are constantly monitored to inform decisions. Public opinion monitoring is of particular importance to governments and intelligence agencies, who seek to monitor extreme views and attempts of radicalizing individuals in society. While social media platforms provide increased visibility and a platform to express public views freely, such platforms can also be used to manipulate public opinion, spread hate speech, and radicalize others. Natural language processing and data mining techniques have gained popularity for the analysis of social media content and the detection of extremists and radical views expressed online. However, existing approaches simplify the concept of radicalization to a binary problem in which individuals are classified as extremists or non-extremists. Such binary approaches do not capture the radicalization process's complexity that is influenced by many aspects such as social interactions, the impact of opinion leaders, and peer pressure. Moreover, the longitudinal analysis of users' interactions and profile evolution over time is lacking in the literature. Aiming at addressing those limitations, this work proposes a sophisticated framework for the analysis of the temporal behavior of extremists on social media platforms. Far-right extremism during the Trump presidency was used as a case study, and a large dataset of over 259,000 tweets was collected to train and test our models. The results obtained are very promising and encourage the use of advanced social media analytics in the support of effective and timely decision-making.Index Terms-smart cities, social media analytics, extreme views, temporal behavior, natural language processing. I. INTRODUCTIONFuture smart cities aim at achieving sustainability and quality of life using a combination of smart technologies [1]. To attain such a goal, smart cities rely on a data-centric approach in which assets, people, and events are constantly monitored, and

A Bibliometric Analysis of Text Mining: Exploring the Use of Natural Language Processing in Social Media Research

“…Apart from these observations, it can be noted that a small portion of the papers deal with political issues (63 papers); most of the papers in this area focused on issues related to political communications, political views of specific countries, political popularity, political marketing, political diffusion, emotions towards candidates during electoral elections, identifying political bots, the refugee crisis, the Ukraine war situation, etc. In terms of political radicalization, the paper by El Barachi et al [55] distinguishes the use of NLP for analyzing the temporal behavior of extremists on social media, having as a focus point, farright extremism during the Trump presidency and a number of 259,000 tweets. The authors highlighted that the results obtained through their research are encouraging in the use of advanced social media analytics in the support of effective and timely decision-making [55].…”

“…In terms of political radicalization, the paper by El Barachi et al [55] distinguishes the use of NLP for analyzing the temporal behavior of extremists on social media, having as a focus point, farright extremism during the Trump presidency and a number of 259,000 tweets. The authors highlighted that the results obtained through their research are encouraging in the use of advanced social media analytics in the support of effective and timely decision-making [55].…”

A Comprehensive Survey of Detection and Prevention Approaches for Online Radicalization: Identifying Gaps and Future Directions

“…Barachi et al [110] proposed a system for detecting online extremist activity utilizing NLP and data mining tools. The authors of this study concentrated on far-right activity in the United States during Trump's presidency, collecting around 250k tweets including neutral and extremist statements.…”

“…Study Approach Dataset Type Mitigation Techniques 2023 [79] ML Imbalanced Na 2023 [101] Graph Imbalanced Na 2022 [21] ML,DL Imbalanced SMOTE 2022 [23] ML Balanced Na 2022 [22] ML,DL Balanced Na 2022 [61] ML Balanced Na 2022 [26] ML Imbalanced SMOTE 2022 [106] DL Imbalanced Na 2022 [28] DL Imbalanced weighted loss function 2022 [107] DL Balanced Na 2022 [108] DL Imbalanced oversampling, undersampling 2022 [110] Clustering Imbalanced SMOTE 2022 [114] Analysis Balanced Na 2022 [65] Analysis Balanced Na 2022 [98] Graph Balanced Na 2022 [19] Graph Imbalanced Na 2021 [60] ML Imbalanced undersampling 2021 [70] ML Imbalanced Na 2021 [85] DL Imbalanced oversampling, undersampling 2021 [79] DL Imbalanced oversampling, undersampling 2021 [115] Analysis Imbalanced weighted sampling 2021 [67] Analysis Imbalanced Na 2021 [118] Analysis Na Na 2021 [96] Graph Imbalanced Na 2021 [20] Graph Balanced Na 2021 [99] Graph Imbalanced oversampling 2020 [54] ML Imbalanced oversampling, undersampling 2020 [55] ML Imbalanced oversampling, undersampling 2020 [24] ML Imbalanced Na 2020 [91] ML Imbalanced SMOTE 2020 [58] ML Imbalanced SMOTE 2020 [81] ML Imbalanced SMOTE 2020 [27] ML Balanced Na 2020 [116] Analysis Imbalanced SMOTE 2020 [57] ML Imbalanced oversampling , undersampling 2019 [59] ML Imbalanced oversampling , undersampling 2019 [63] ML Imbal...…”