Deteksi Threat dan Vulnerability pada Twitter menggunakan Algoritma Support Vector Machine
Abstract
Abstrak—Di era globalisasi, perkembangan internet di bidang teknologi informasi menimbulkan kejahatan yang merugikan banyak pihak. Hal ini disebabkan adanya threat dan vulnerability terhadap sistem keamanan. Threat dan vulnerability ini dapat ditemukan di Twitter karena banyak pengguna memposting kejahatan sistem secara bebas di Twitter. Maka, pendeteksian threat dan vulnerability di Twitter dilakukan dengan menggunakan algoritma Support Vector Machine (SVM). Proses dalam penelitian ini adalah teks akan dikumpulkan menjadi sebuah dataset, diberi label, teks pre-processed, kemudian diberikan metode pembobotan yaitu metode POS Tagging dan Term Frequency – Inverse Document Frequency (TF-IDF), dan data akan dilatih agar algoritma SVM dapat mengklasifikasikan data untuk mendapatkan nilai akurasi, presisi, recall dan F1-Score. Pada Tugas Akhir ini, pengambilan data Twitter dengan total 4270 data, dengan data positif 2135 dan data negatif 2135 dan 90% dataset digunakan untuk data latih dan 10% untuk data pengujian. Dari hasil pengujian performansi didapatkan nilai akurasi sebesar 89%, presisi sebesar 89%, recall sebesar 89% dan F1-Score Pengujian parameter Gamma dan C terbaik sebesar 30000 anis 89%.Kata kunci— threat, support vector machine, text preproessing, TF-IDF, vulnerability, Twitter
References
[1] A. Baccouche, S. Ahmed, D. Sierra-Sosa, and A. Elmaghraby,
comments and emails,= Information (Switzerland), vol. 11, no.
6, 2020, doi: 10.3390/info11060312.
[2] S. Samtani, R. Chinn, H. Chen, and J. F. Nunamaker,
Proactive Cyber Threat Intelligence,= Journal of Management
Information Systems, vol. 34, no. 4, pp. 1023–1053, 2017, doi:
10.1080/07421222.2017.1394049.
[3] A. T. Tunggal,
https://www.upguard.com/blog/cyber-threat (accessed Dec.
16, 2021).
[4] A. T. Tunggal,
https://www.upguard.com/blog/vulnerability (accessed Dec.
16, 2021).
[5] L. Qiu, H. Lin, J. Ramsay, and F. Yang,
tweet: Personality expression and perception on Twitter,=
Journal of Research in Personality, vol. 46, pp. 710–718, Dec.
2012, doi: 10.1016/j.jrp.2012.08.008.
[6] L. Liu, C. Chen, J. Zhang, O. De Vel, and Y. Xiang,
Threat Identification Using the Simultaneous Neural Learning
of Multi-Source Logs,= IEEE Access, vol. 7, pp. 183162–
183176, 2019, doi: 10.1109/ACCESS.2019.2957055.
[7] K. Liu,
Network,= 2019 5th International Conference on Big Data and
Information Analytics (BigDIA), pp. 114–119, 2019.
[8] B. Zhao,
10.1007/978-3-319-32001-4.
[9] A. T. Korkmaz, M. Ulaş, M. Karabatak, Y. Santur, and A.
Tunahan Korkmaz,
and Applications=, Accessed: Aug. 14, 2022. [Online].
Available: https://www.icaens.com/
[10]Y. Chen,
maximum entropy,= Proceedings - 2015 International
Conference on Intelligent Transportation, Big Data and Smart
City, ICITBS 2015, pp. 81–84, Jan. 2016, doi:
10.1109/ICITBS.2015.26.
[11]A. S. Shafie, N. M. Sharef, M. A. A. Murad, and A. Azman,
Dependency Relation in Aspect-based Sentiment Analysis,=
Proceedings - 2018 4th International Conference on
Information Retrieval and Knowledge Management: Diving
into Data Sciences, CAMP 2018, pp. 107–112, Sep. 2018, doi:
10.1109/INFRKM.2018.8464692.
[12]E. Erizal and C. Setianingsih,
Indonesian Language on Instagram Comment Section Using
Maximum Entropy Classification Method,= 2019 International
Conference on Information and Communications Technology
(ICOIACT), pp. 533–538, 2019.
[13]R. Xu,
for an MOOC search engine,= ICALIP 2014 - 2014
International Conference on Audio, Language and Image
Processing, Proceedings, pp. 868–873, Jan. 2015, doi:
10.1109/ICALIP.2014.7009919.
[14]M. Amjad, N. Ashraf, A. Zhila, G. Sidorov, A. Zubiaga, and A.
Gelbukh,
Identification in Urdu Tweets,= IEEE Access, vol. 9, pp.
128302–128313, 2021, doi: 10.1109/ACCESS.2021.3112500.
[15]H. Tabrizchi, M. M. Javidi, and V. Amirzadeh,
residential building energy consumption using a multi-verse
optimizer-based support vector machine with k-fold crossvalidation,= Evolving Systems, vol. 12, no. 3, pp. 755–767,
Sep. 2021, doi: 10.1007/S12530-019-09283-8.
[16]K. L. Sumathy,
and Issues – An Overview,= vol. 80, no. 4, pp. 29–32, 2013.
