Multiclass Classification for Cyber Threats Detection on Twitter
Source abstract
Abstract
The advances in technology increase the number of internet systems usage. As a result, cybersecurity issues have become more common. Cyber threats are one of the main problems in the area of cybersecurity. However, detecting cybersecurity threats is not a trivial task and thus is the center of focus for many researchers due to its importance. This study aims to analyze Twitter data to detect cyber threats using a multiclass classification approach. The data is passed through different tasks to prepare it for the analysis. Term Frequency and Inverse Document Frequency (TFIDF) features are extracted to vectorize the cleaned data and several machine learning algorithms are used to classify the Twitter posts into multiple classes of cyber threats. The results are evaluated using different metrics including precision, recall, F-score, and accuracy. This work contributes to the cyber security research area. The experiments revealed the promised results of the analysis using the Random Forest (RF) algorithm with (F-score = 81%). This result outperformed the existing studies in the field of cyber threat detection and showed the importance of detecting cyber threats in social media posts. There is a need for more investigation in the field of multiclass classification to achieve more accurate results. In the future, this study suggests applying different data representations for the feature extraction other than TF-IDF such as Word2Vec, and adding a new phase for feature selection to select the optimum features subset to achieve higher accuracy of the detection process.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Network Security and Intrusion Detection · Advanced Malware Detection Techniques · Cybercrime and Law Enforcement Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (44)
Show source-provided references
1. Are social media users more satisfied with their life than non-users? A study on older Italians10.1017/S0144686X21000416 ↗
2. A review: Cybersecurity challenges and their solutions in connected and autonomous vehicles (CAVs)10.12962/jaree.v7i1.322 ↗
3. Learning cyber security and machine engineering at the university10.34306/bfront.v3i1.242 ↗
4. Cyber threat detection: Unsupervised hunting of anomalous commands (UHAC)10.1016/j.dss.2023.113928 ↗
5. Almazroi · Deep Learning Approaches for Spoken and Natural Language Processing · 2021 · 5510.1007/978-3-030-79778-2_4 ↗
6. Alshaikh · Int. Conf. on Ubiquitous Security · 2023 · 54510.1007/978-981-99-0272-9_38 ↗
7. A machine learning approach for the NLP-based analysis of cyber threats and vulnerabilities of the healthcare ecosystem10.3390/s23020651 ↗
8. Automated machine learning enabled cybersecurity threat detection in Internet of Things environment10.32604/csse.2023.030188 ↗
9. Shaukat · 2020 Int. Conf. on Cyber Warfare and Security (ICCWS) · 2020 · 1
10. Research on threat detection in cyber security based on machine learning
11. Apruzzese · 2018 10th Int. Conf. on Cyber Conflict (CyCon) · 2018 · 37110.23919/CYCON.2018.8405026 ↗
12. D. Nandakumar, R. Schiller, C. Redino, K. Choi, A. Rahman et al., “Zero day threat detection using metric learning autoencoders,” arXiv preprint arXiv:2211.00441, 2022.10.1109/ICMLA55696.2022.00210 ↗
13. Andresini · Machine Intelligence and Big Data Analytics for Cybersecurity Applications · 2021 · 10510.1007/978-3-030-57024-8_5 ↗
14. Real-time content-based cyber threat detection with machine learning
15. Software defined network enabled fog-to-things hybrid deep learning driven cyber threat detection system
16. Minority resampling boosted unsupervised learning with hyperdimensional computing for threat detection at the edge of Internet of things10.1109/ACCESS.2021.3111053 ↗
17. Performance of machine learning-based multi-model voting ensemble methods for network threat detection in Agriculture 4.010.3390/s21227475 ↗
18. Deep learning approach for enhanced cyber threat indicators in Twitter stream
19. A new hybrid machine learning for cybersecurity threat detection based on adaptive boosting10.1080/08839514.2019.1582861 ↗
20. Raval · Versatile Cybersecurity · 2018 · 1910.1007/978-3-319-97643-3_2 ↗
21. Evaluation of ensemble machine learning methods in mobile threat detection
22. Corpus and deep learning classifier for collection of cyber threat indicators in twitter stream
23. Sentiment analysis of COVID-19 tweets from selected hashtags in Nigeria using VADER and Text Blob analyser10.1186/s43067-023-00070-9 ↗
24. Role of text pre-processing in twitter sentiment analysis10.1016/j.procs.2016.06.095 ↗
25. Effective text data preprocessing technique for sentiment analysis in social media data
26. Wisdom · An Introduction to Twitter Data Analysis in Python · 2016
27. NLTK: The natural language toolkit
28. NLTK, “NLTK stopwords list,” 2023. [Online]. Available: https://www.nltk.org/search.html?q=stopwords
29. M. F. Porter, “Snowball: A language for stemming algorithms,” 2001. Available: http://snowball.tartarus.org/
30. Classification and diagnostic prediction of breast cancer metastasis on clinical data using machine learning algorithms10.1038/s41598-023-27548-w ↗
31. Understanding bag-of-words model: A statistical framework10.1007/s13042-010-0001-0 ↗
32. Understanding inverse document frequency: On theoretical arguments for IDF10.1108/00220410410560582 ↗
33. A statistical approach to mechanized encoding and searching of literary information10.1147/rd.14.0309 ↗
34. A statistical interpretation of term specificity and its application in retrieval10.1108/eb026526 ↗
35. Analysis of a multiclass classification problem by lasso logistic regression and singular value decomposition to identify sound patterns in queenless bee colonies10.1016/j.compag.2019.02.024 ↗
36. One-vs-one multiclass least squares support vector machines for direction of arrival estimation
37. A probabilistic multi-class strategy of one-vs.-rest support vector machines for cancer classification10.1016/j.neucom.2008.04.033 ↗
38. SWATAC: A sentiment analyzer using one-vs-rest logistic regression
39. Ensemble of random forests One vs. Rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares10.1016/j.jneumeth.2017.12.005 ↗
40. A fine-tuned BERT-based transfer learning approach for text classification10.1155/2022/3498123 ↗
41. Cluster analysis on COVID-19 outbreak sentiments from twitter data using K-means algorithm
42. M. Chen, K. Q. Weinberger and F. Sha, “An alternative text representation to TF-IDF and Bag-of-Words,” arXiv preprint arXiv:1301.6770, 2013.
43. K. Alperin, E. Joback, L. Shing and G. Elkin, “A framework for unsupervised classificiation and data mining of tweets about cyber vulnerabilities,” arXiv preprint arXiv:2104.11695, 2021.
44. Threatening URDU language detection from tweets using machine learning10.3390/app122010342 ↗