Analisis Forensik Digital Pada Komentar Youtube Live Menggunakan Sentiment Analysis
DOI:
https://doi.org/10.30989/teknomatika.v15i1.1115Keywords:
Sentiment Analysis, Digital Forensics, TF-IDF, Cosine Similarity, YoutubeAbstract
The development of increasingly sophisticated technology can have a positive influence on various aspects of our daily lives. From the survey results of the Indonesian Internet Services Association (APJII) in the second quarter of 2019-2020, it shows that Internet users of the operator spend more time watching online videos. Youtube video content watching is open to the public and all ages can freely watch it. However, the content and comments are not necessarily suitable for audiences of all ages to read. Of course, Youtube video content can also affect behavior, especially minors.The purpose of this research is to conduct digital forensic analysis on Youtube Live Comments using sentiment analysis.The research method used applies the NIST SP 800-86 method, namely Collection, Examination, Analysis, and Reporting. Sentiment analysis resulted in 0.01 in the comments on the two videos tested, namely the PUBG and Free Fire video games. Sentiment analysis resulted in 0.01 in the comments on the two videos tested, namely the PUBG and Free Fire video games.
References
[2] N. Anwar, “Analisis Investigasi Forensik WhatsApp Messenger Smartphone Terhadap WhatsApp Berbasis Web,” Jurnal Ilmu Teknik Elektro Komputer dan Informatika (JITEKI), vol. 3, pp. 1–10, 2017.
[3] A. N. Muhammad, “Analisis Sentimen Positif dan Negatif Komentar Video Youtube Menggunakan Metode Naïve Bayes – Support Vector Machine (NBSVM) Classifier’.,” 2019.
[4] D. Hariyadi, M. Wahyu Indriyanto, and Muhammad Habibi, “Analisis Barang Bukti Digital Aplikasi Paziim Pada Ponsel Paziim Digital Evidence Analysis Application On Android,” vol. 2, pp. 52–56, 2019.
[5] F. I. Tanesab, I. Sembiring, and H. D. Purnomo, “Sentiment Analysis Model Based On Youtube Comment Using Support Vector Machine,” nternational Journal of Computer Science and Software Engineering (IJCSSE), vol. 6 No.8, pp. 180–185, 2017.
[6] Hariani, “Analisis Bukti Digital Cyberbullying Pada Jejaring Sosial Menggunakan Naïve Bayes Classifier (Nbc),” 2017.
[7] K. N. Adi and D. Sebastian, “Pembentukan Dataset Topik Kata Bahasa Indonesia pada Twitter Menggunakan TF-IDF & Cosine Similarity,” Jurnal Teknik Informatika dan Sistem Informasi, vol. 4, pp. 2229–2443, 2018.
[8] P. Y. Saputra, “Implementasi Sentimen Analisis Komentar Channel Video Pelayanan Pemerintah Di Youtube Menggunakan,” Polinema, Jurnal Informatika, pp. 209–213, 2019.
[9] M. Muliadin, “Kebijakan Kriminal dalam Menanggulangi Kejahatan Kesusilaan Melalui Internet Pendahuluan masyarakat . Hal ini telah menyebabkan perubahan cara berpikir dan bertindak (Electronic Funds Transfer System atau sistem transfer dana elektronik),” vol. 8 No.2, pp. 167–181, 2020.
[10] K. Kent, “Penerapan Metode Composite Logic Untuk Perancangan Framework Pengumpulan Bukti Digital Pada Media Sosial,” ILKOM Jurnal Ilmiah, pp. 1–121, 2006.
[11] A. Indriani, “Analisa Perbandingan Metode Naïve Bayes Classifier Dan K-Nearest Neighbor Terhadap Klasifikasi Data,” Sebatik, vol. 24, no. 1, pp. 1–7, Jun. 2020, doi: 10.46984/sebatik.v24i1.909.
[12] M. N. Al Jum’ah, “Penerapan Metode Composite Logic Untuk Perancangan Framework Pengumpulan Bukti Digital Pada Media Sosial,” ILKOM Jurnal Ilmiah, vol. 11 No.2, 2019.
