Pemodelan Sentimen Komentar YouTube Berbasis Naive Bayes

Hari Murti; Rara Sriartati Redjeki; Novita Mariana; Agus Prasetyo Utomo; Widiyanto Tri Handoko

doi:10.55606/jitek.v6i1.8767

Authors

Hari Murti Universitas Stikubank
Rara Sriartati Redjeki Universitas Stikubank
Novita Mariana Universitas Stikubank
Agus Prasetyo Utomo Universitas Stikubank
Widiyanto Tri Handoko Universitas Stikubank

DOI:

https://doi.org/10.55606/jitek.v6i1.8767

Keywords:

Social Network Analysis, NetworkX, Degree Centrality, Edgelist, Phyton

Abstract

Social Network Analysis (SNA) is a crucial quantitative methodology for mapping relationships and identifying connectivity structures within a group. This research specifically explores the use of the NetworkX library in Python as an effective tool for analyzing social networks. The primary objective of this study is to apply the Degree Centrality method to measure the level of connectivity and identify the most popular actors in a social network. The methodology employed is the quantitative analysis of an undirected graph modeled from the us_edgelist.csv dataset, which contains a list of relationships among political figures in an edge list format. Data processing utilized pandas, and the graph object was constructed using NetworkX. Degree Centrality was calculated for each node, with the results being normalized to provide a relative value. This normalization allows for a direct comparison of how active each actor is within the network. The centrality results were then visualized, with node sizes adjusted based on their Degree Centrality score. The results of the analysis indicate that figures like Bush and Obama possess the highest Degree Centrality score, 0.25, suggesting they have the greatest number of direct connections in this network. This high value confirms their role as the most active or central actors in the exchange and interaction within the political network studied. This finding validates the effectiveness of Degree Centrality as an indicator of high involvement. The study concludes that the implementation of Social Network Analysis using NetworkX provides a robust framework for understanding political relationship structures. Therefore, Degree Centrality is a reliable metric for quantifying actor activity and accurately identifying individuals who form the center of connections within the network.

References

[1] A. N. Pratama and D. A. Prasetyo, "Analisis Peran YouTube Sebagai Media Penyebaran Informasi di Era Digital," Jurnal Ilmu Komputer dan Informasi, vol. 15, no. 2, pp. 45–52, 2024.

[2] B. W. Susanto and C. R. Sari, "Karakteristik Bahasa Komentar Netizen di Media Sosial dan Tantangannya bagi Analisis Sentimen," Prosiding Seminar Nasional Komputer dan Teknologi Informasi (SNKTI), pp. 110–116, 2023.

[3] J. Siregar and F. Rahman, "A Review of Sentiment Analysis Techniques and Applications: From Machine Learning to Deep Learning," IEEE Access, vol. 11, pp. 25000-25015, 2023.

[4] F. A. Ginting and K. A. Laksmi, "Klasifikasi Sentimen Teks menggunakan Metode Support Vector Machine (SVM) dan Naive Bayes," Jurnal Informatika dan Rekayasa Perangkat Lunak, vol. 5, no. 1, pp. 30–38, 2021.

[5] B. Wijaya and L. Setiawan, "Perbandingan Akurasi Klasifikasi Sentimen antara Metode Manual dan Otomatis," Seminar Nasional Teknologi Informasi dan Komunikasi (SENDIKA), pp. 400–405, 2022.

[6] C. Putra and D. Yulianto, "Optimasi Algoritma Naive Bayes untuk Klasifikasi Teks dengan Fitur N-Gram," Jurnal Rekayasa Informasi dan Teknologi, vol. 9, no. 3, pp. 150–158, 2020.

[7] N. Ramadhan and O. Dewi, "Penerapan Teorema Bayes dalam Pemodelan Probabilitas Klasifikasi Data," Jurnal Sains dan Teknologi, vol. 2, no. 1, pp. 1–7, 2024.

[8] T. Simanjuntak and P. M. Wibowo, "Pemilihan Fitur Terbaik dalam Analisis Sentimen Menggunakan Information Gain," International Journal of Advances in Data Science, vol. 7, no. 2, pp. 100–108, 2025.

[9] K. Sari and R. Abdullah, "Sentiment Analysis on Indonesian Tweets using Naive Bayes and Lexicon-Based Approach," TELKOM-NIKA (Telecommunication Computing Electronics and Control), vol. 18, no. 6, pp. 3000–3008, 2020.

[10] M. Putra and S. Dewi, "Machine Learning for Social Media Data Analysis: A Focus on YouTube Comments," IEEE Transactions on Computational Social Systems, vol. 8, no. 4, pp. 800–810, 2021.

[11] M. N. Hidayat and S. T. Wibawa, "Analisis Sentimen Komentar Video Politik di YouTube dengan Naive Bayes Classifier," Jurnal Informatika, vol. 13, no. 1, pp. 50–59, 2022.

[12] S. Rahayu and K. Putri, "Performance Evaluation of Naive Bayes on Sentiment Classification with Different Preprocessing Tech-niques," International Journal of Computer Applications, vol. 175, no. 3, pp. 15–20, 2023.

[13] O. P. Siregar and V. R. P. Hutagalung, "A Comparative Study of Machine Learning Algorithms for Sentiment Analysis on Product Reviews," Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 11, no. 5, pp. 1000–1008, 2024.

[14] P. Dewi and N. Sari, "Challenges and Opportunities of Sentiment Analysis on Informal Indonesian Language in Social Media," Journal of Informatics Engineering and Computer Science (JIECOM), vol. 5, no. 1, pp. 10–18, 2025.

[15] R. F. Akbar and Z. Lubis, "Improved Naive Bayes with Feature Selection for Sentiment Analysis on Movie Reviews," International Journal of Artificial Intelligence and Robotics, vol. 4, no. 1, pp. 50–57, 2020.

[16] K. P. Sitompul and Y. B. Simatupang, "Klasifikasi Sentimen Berita Online Menggunakan Naive Bayes dan Pembobotan TF-IDF," Jurnal Sistem Informasi Bisnis (JSINBIS), vol. 10, no. 2, pp. 120–128, 2021.

[17] S. T. Sitohang and Z. A. Manurung, "Text Preprocessing Techniques in Indonesian Sentiment Analysis: A Comparative Study," Journal of Big Data Science and Technology, vol. 3, no. 1, pp. 1–10, 2022.

[18] O. P. Siregar and A. M. H. Damanik, "Deep Learning vs. Machine Learning in Sentiment Analysis: A Performance Review," IEEE Conference on Big Data (BigData), pp. 1500–1509, 2023.

[19] U. P. Sitorus and B. C. Sihotang, "Sentiment Analysis of YouTube Comments on Education Videos: A Naive Bayes Approach," International Journal of Advanced Trends in Computer Science and Engineering, vol. 13, no. 2, pp. 2500–2507, 2024.

[20] Z. Tampubolon and E. H. Purba, "Optimalisasi Parameter Naive Bayes untuk Klasifikasi Sentimen Multikelas," Jurnal Riset Komputer, vol. 7, no. 3, pp. 180–188, 2025.