Abstract
Extremism is a growing threat worldwide that presents a significant danger to public safety and national security. Social networks provide extremists with spaces to spread their ideas through commentaries or tweets, often in Asian English. In this paper, we propose an intelligent approach that cleans the text’s content, analyzes its sentiment, and extracts its features after converting it to digital data for machine learning treatments. We apply 16 intelligent machine learning classifiers for extremism detection and classification. The proposed artificial intelligence methods for Asian English language data are used to extract the essential features from the text. Our evaluation of the proposed model with an extremism dataset proves its effectiveness compared to the standard classification models based on various performance metrics. The proposed model achieves 93,6% accuracy for extremism detection and 97,0% for extremism classification.
- [1] . 1994. Accuracy (Trueness and precision) of measurement methods and results - Part 1: General principles and definitions. 1.Google Scholar
- [2] . 2011. Data Mining. Mining of Massive Datasets. 1–17.
DOI: Google ScholarCross Ref
- [3] . 2020. Detecting Violent Radical Accounts on Twitter, Vol. 11. 1 pages.Google Scholar
Cross Ref
- [4] . 2015. Using a KNN and SVM-based One-class Classifier to Detect Online Radicalization on Twitter. In International Conference on Distributed Computing and Internet Technology. 431–442.Google Scholar
- [5] . 2011. An overview and classification of approaches to information extraction in wireless sensor networks.Google Scholar
- [6] . 2020. Social media usage for enhancing English language skill. (2020).Google Scholar
- [7] . 2015. Detecting jihadist messages on Twitter. In 2015 European Intelligence and Security Informatics Conference. 161–164.
DOI: Google ScholarDigital Library
- [8] . 2010. Data Mining and Machine Learning in Astronomy, Vol. 19. arXiv:0906.2173v2 [astro-ph.IM]. 1049–1106.
DOI: Google ScholarCross Ref
- [9] . 2019. Introduction to Scikit-learn. Springer, 215–229.
DOI: DOI: https://doi.org/978-1-4842-4470-8_18Google Scholar - [10] . 2020. The statistics of English across Asia. The Handbook of Asian Englishes. 49–80.Google Scholar
Cross Ref
- [11] . 2018. The problem of data cleaning for knowledge extraction from social media. Springer.
DOI: Google ScholarCross Ref
- [12] . 2011. Social media data mining- a social network analysis of tweets during the 2010-2011 Australian floods. Pacific Asia Conference on Information Systems (PACIS) (July 2011), 5–9.Google Scholar
- [13] . 2012. “Terribly beautiful!” (terribly beautiful): A Subjectivity Lexicon for Dutch Adjectives. In LREC. 3568–3572.Google Scholar
- [14] . 2011. Guide to the Drivers of Violent Extremism. United States Agency for International Development.Google Scholar
- [15] . 2014. Echo Chamber or Public Sphere? Predicting Political Orientation and Measuring Political Homophily in Twitter using Big Data. Number 64, 317–332.Google Scholar
- [16] . 2016. Research-paper Recommender Systems: A Literature Survey, Vol. 17. International Journal on Digital Libraries. 305–338.
DOI: DOI: https://doi.org/s00799-015-0156-0Google Scholar - [17] . 2015. Map as a service: A framework for visualising and maximising information return from multi-modal wireless sensor networks. Sensors 15, 9 (2015), 22970–23003.Google Scholar
Cross Ref
- [18] . 2012. English language education in East Asia: Some recent developments. Journal of Multilingual and Multicultural Development 33, 4 (2012), 345–362.
DOI: arXiv:Google ScholarCross Ref
- [19] . 2020. A survey of context-aware access control mechanisms for cloud and fog networks: Taxonomy and open research issues. Sensors 20, 9 (2020), 2464.Google Scholar
Cross Ref
- [20] . 2021. A survey on data cleaning methods for improved machine learning model performance. arXiv.
DOI: Google ScholarCross Ref
- [21] . 2006. Theory of Point Estimation. Springer Science & Business Media.Google Scholar
- [22] . 2022. A Classification of Antifa Twitter Accounts based on Social Network Mapping and Linguistic Analysis, Vol. 12.
DOI: Google ScholarCross Ref
- [23] . 2016. Tweet sentiment analysis by incorporating sentiment-specific word embedding and weighted text features. In 2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI’16). 568–571.
DOI: Google ScholarCross Ref
- [24] . 2017. Online extremism and the communities that sustain it: Detecting the ISIS supporting community on Twitter. 12, 12.
DOI: Google ScholarCross Ref
- [25] . 2022. Impact of social media on learning English language during the COVID-19 pandemic. PSU Research Review (2022).Google Scholar
Cross Ref
- [26] . 2020. On detecting online radicalization and extremism using natural language processing. In 2020 21st International Arab Conference on Information Technology (ACIT’20). IEEE, 1–5.
DOI: Google ScholarCross Ref
- [27] . 2011. Evaluation: From Precision, Recall and F-measure to ROC, Informedness, Markedness and Correlation. arXiv:2010.16061v1. 37–63.
DOI: Google ScholarCross Ref
- [28] . 2019. Analysis of Twitter specific preprocessing technique for tweets.
DOI: Google ScholarDigital Library
- [29] . 2019. The Role of English as a Global Language, Vol. 4. 65–79.Google Scholar
- [30] . 2020. An ensemble based machine learning model for diabetic retinopathy classification. In 2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE’20). 1–6.
DOI: Google ScholarCross Ref
- [31] . 2021. Understanding the language of ISIS: An empirical approach to detect radical content on Twitter using machine learning. 2, 66, 1075–1090.
DOI: Google ScholarCross Ref
- [32] . September 2014. Using publicly visible social media to build detailed forecasts of civil unrest (September 2014).
DOI: Google ScholarCross Ref
- [33] . 2015. Applying social media intelligence for predicting and identifying on-line radicalization and civil unrest oriented threats.Google Scholar
- [34] . 2017. A semantic graph-based approach for radicalisation detection on social media. In The Semantic Web, , , , , , and (Eds.). Springer International Publishing, Cham, 571–587.Google Scholar
- [35] . 2020. Improvised Technique for Analyzing Data and Detecting Terrorist Attack Using Machine Learning Approach Based on Twitter Data. Journal of Computer and Communications, Vol. 7 8, 50–62.
DOI: Google ScholarCross Ref
- [36] . 2022. https://scikit-learn.org/stable/modules/generated/sklearn.svm.LinearSVC.html.Google Scholar
- [37] . 2020. Detecting suspicious texts using machine learning techniques. 18, 10, 1075–1090.Google Scholar
- [38] . 2019. Psychological mechanisms involved in radicalization and extremism. A rational emotive behavioral conceptualization. Frontiers in Psychology.
DOI: Google ScholarCross Ref
- [39] . 2020. Policy specification and verification for blockchain and smart contracts in 5G networks. ICT Express 6, 1 (2020), 43–47.Google Scholar
Cross Ref
- [40] . 2020. Detecting East Asian Prejudice on Social Media. (2020).
DOI: Google ScholarCross Ref
- [41] . 2019. Mazajak: An online Arabic sentiment analyser. Proceedings of the Fourth Arabic Natural Language Processing Workshop. 192–198.Google Scholar
- [42] . 2009. Mean squared error: Love it or leave it? A new look at signal fidelity measures. IEEE Signal Processing Magazine 26, 1 (2009), 98–117.Google Scholar
Cross Ref
Index Terms
An Intelligent Approach Based on Cleaning up of Inutile Contents for Extremism Detection and Classification in Social Networks
Recommendations
Contagion dynamics of extremist propaganda in social networks
Recent terrorist attacks carried out on behalf of ISIS on American and European soil by lone wolf attackers or sleeper cells remind us of the importance of understanding the dynamics of radicalization mediated by social media communication channels. In ...
Content-based emotion classification in online social networks for Chinese Microblogs
ACSW '17: Proceedings of the Australasian Computer Science Week MulticonferenceRecent years, social networks are popular throughout the whole world. In China in particular, more people spend their time on social networks. Sina Weibo, as the most popular microblogs in China, records millions of microblogs from different population. ...
Extremism Propagation in Social Networks with Hubs
One aspect of opinion change that has been of academic interest is the impact of people with extreme opinions (extremists) on opinion dynamics. An agent-based model has been used to study the role of small-world social network topologies on general ...






Comments