Hybrid Lexicon and Logistic Regression Sentiment Analysis of YouTube Comments on Suharto’s National Hero Designation

DOI: https://doi.org/10.33650/jeecom.v8i1.16845
Authors

(1) * Laksmita Dewi Supraba   (Universitas Walisongo Gempol Pasuruan Jawa Timur)  
        Indonesia
(2)  Andi Sunyoto   (Postgraduate Amikom University Yogyakarta Indonesia)  
        Indonesia
(3)  Setyo N   (Universitas Walisongo Gempol Pasuruan Jawa Timur)  
        Indonesia
(*) Corresponding Author

Abstract


This study proposes a hybrid approach to sentiment analysis by combining lexicon and Logistic Regression methods based on TF-IDF features, and using Multinomial Naive Bayes as a benchmark, to classify YouTube comments related to Suharto's appointment as a National Hero. The dataset contains 500 comments TV taken from five YouTube channels: TalkShow tvOne Reload, Kompas Madiun, Tribunnews, Perspektif, and Tempodotco, 100 comments each. The research stages include text pre-processing, lexicon development, automatic labeling, manual validation of annotations, TF-IDF feature extraction, and sentiment classification. The validation results show a 63% agreement between lexicon labels and manual annotations, with a Cohen's Kappa of 0.15 indicating low inter-annotation agreement. The proposed Logistic Regression framework achieved an overall accuracy of 91%, with a weighted average F1 score of 0.87 and a Macro F1 score of 0.43, slightly better than Naïve Bayes Multinomial, which achieved an accuracy of 90% and a weighted F1 score of 0.85. However, the relatively small performance improvement and high accuracy affected the dominance of the neutral class. The Confusion Matrix for the data shows that the model still has difficulty distinguishing between positive and negative comments the recall for the negative class is 0%, and for the positive class is 20%. Therefore, these results are still preliminary and cannot be generalized.

Keywords

Sentiment Analysis, Lexicon-Based Labeling, Logistic Regression, YouTube Comments, Public Opinion, TF-IDF, Political Historical



Full Text: PDF



References


R. Pradhan, “Extracting Sentiments from YouTube Comments,” in Proceedings of the IEEE International Conference on Image Information Processing, Institute of Electrical and Electronics Engineers Inc., 2021, pp. 142–145. doi: 10.1109/ICIIP53038.2021.9702561.

B. Myagmar, J. Li, and S. Kimura, “Cross-Domain Sentiment Classification with Bidirectional Contextualized Transformer Language Models,” IEEE Access, vol. 7, pp. 163219–163230, 2019, doi: 10.1109/ACCESS.2019.2952360.

A. Bondielli and F. Marcelloni, “A survey on fake news and rumor detection techniques,” Inf. Sci. (N. Y.)., vol. 497, pp. 38–55, Sep. 2019, doi: 10.1016/j.ins.2019.05.035.

S. K. Lora, I. Jahan, R. Hussain, R. Shahriyar, and A. B. M. A. Al Islam, “A transformer-based generative adversarial learning to detect sarcasm from Bengali text with correct classification of confusing text,” Heliyon, vol. 9, no. 12, Dec. 2023, doi: 10.1016/j.heliyon. 2023.e22531.

T. Kushartono, N. Fujilestari, and T. Muhammad Ali Ridho, “Political Journey of Indonesia: Dynamics and Challenges,” International Journal of Science and Research (IJSR), vol. 12, no. 12, pp. 734–740, Dec. 2023, doi: 10.21275/sr231207140923.

M. Adnan dan N. Mona, “Strategi Komunikasi Politik melalui Media Sosial oleh Calon Presiden Indonesia 2024,” Politika: Jurnal Ilmu Politik, vol. 15, no. 1, pp. 1–20, Apr. 2024, doi: 10.14710/politika.15.1.2024.1-20.

Sekretariat Kabinet Republik Indonesia, “Hormati Jasa Para Pendahulu, Presiden Prabowo Anugerahkan Gelar Pahlawan Nasional kepada Sepuluh Tokoh Bangsa.” Accessed: Jul. 07, 2026. [Online]. Available: https://setkab.go.id/gelar-pahlawan-nasional-2025-prabowo/

T. Putri, Siti Nurhaliza, and Dodi Vionanda, “Analisis Sentimen Penggunaan Aplikasi YouTube Menggunakan Metode Naïve Bayes,” UNP Journal of Statistics and Data Science, vol. 3, no. 1, pp. 60–66, Feb. 2025, doi: 10.24036/ujsds/vol3-iss1/343.

A. S. Jessica Adinda Student, C. Author, and A. S. Jessica Adinda, “Journal of Humanities and Social Sciences Studies the Victim Narrative of the 1965-1966 Massacre in Indonesia as A Biopicture,” 2022, doi: 10.32996/jhsss.

N. Mahfudza and M. Ihksan, “Sentiment Analysis of YouTube Comments on Indonesian Presidential Candidates in 2024 using Naïve Bayes Classifier,” JURIKOM (Jurnal Riset Komputer), vol. 12, no. 2, pp. 140–148, Apr. 2025, doi: 10.30865/jurikom. v12i2.8538.

A. M. Firdaus, N. Ibrahim, and K. Kurniawati, “Hubungan Diplomatik Indonesia-Brunei Darussalam Pada Masa Presiden Suharto & Sultan Hassanal Bolkiah, 1984-1998,” Jurnal Humanitas: Katalisator Perubahan dan Inovator Pendidikan, vol. 10, no. 1, pp. 140–155, Dec. 2023, doi: 10.29408/jhm. v10i1.23965.

R. Widjayanto and M. Huseini, “Transformasi Organisasi Sekretariat Kabinet Republik Indonesia dari Era Presiden Soeharto Sampai Presiden Joko Widodo,” Jurnal Manajemen dan Ilmu Administrasi Publik (JMIAP), vol. 5, no. 4, pp. 402–415, Dec. 2023, doi: 10.24036/jmiap. v5i4.777.

S. Ratnaswari, N. C. Wibowo, and D. S. Y. Kartika, “Analisis Sentimen Menggunakan Metode Lexicon-Based dan Support Vector Machine pada Presiden dan Wakil Presiden Indonesia Periode 2024–2029,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, no. 1, Jan. 2025, doi: 10.23960/jitet. v13i1.5604.

J. E. Br Sinulingga and H. C. K. Sitorus, “Analisis Sentimen Opini Masyarakat terhadap Film Horor Indonesia Menggunakan Metode SVM dan TF-IDF,” Jurnal Manajemen Informatika (JAMIKA), vol. 14, no. 1, pp. 42–53, Feb. 2024, doi: 10.34010/jamika.v14i1.11946.

S. Pesina and L. G. Yusupova, “Words Functioning in Lexicon,” Procedia Soc. Behav. Sci., vol. 192, pp. 38–43, Jun. 2015, doi: 10.1016/j.sbspro.2015.06.006.

I. Cero, J. Luo, and J. M. Falligant, “Lexicon-Based Sentiment Analysis in Behavioral Research,” Perspect. Behav. Sci., vol. 47, no. 1, pp. 283–310, Mar. 2024, doi: 10.1007/s40614-023-00394-x.

S. A. Rahmadhani, L. D. Rusanti, and H. Al Rosyid, “Klasifikasi Sentimen Komentar Youtube Demonstrasi DPR RI Menggunakan Support Vector Machine,” Arcitech: Journal of Computer Science and Artificial Intelligence, vol. 5, no. 2, pp. 356–375, Dec. 2025, doi: 10.29240/arcitech. v5i2.15316.

P. C. Shilpa, R. Shereen, S. Jacob, and P. Vinod, “Sentiment analysis using deep learning,” in Proceedings of the 3rd International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2021, Institute of Electrical and Electronics Engineers Inc., Feb. 2021, pp. 930–937. doi: 10.1109/ICICV50876.2021.9388382.

A. Novanto, D. Indra, and W. Astuti, “Analisis Pre-processing Sentimen Terhadap Komentar Layanan Indihome Pada Twitter,” Buletin Sistem Informasi dan Teknologi Islam, vol. 5, no. 1, pp. 30–36, Feb. 2024, doi: 10.33096/busiti. v5i1.2066.

M. L. Lewis and M. C. Frank, “The length of words reflects their conceptual complexity,” Cognition, vol. 153, pp. 182–195, Aug. 2016, doi: 10.1016/j.cognition.2016.04.003.

J. Pardede and D. Darmawan, “PERBANDINGAN ALGORITMA STEMMING PORTER, SASTRAWI, IDRIS, DAN ARIFIN & SETIONO PADA DOKUMEN TEKS BAHASA INDONESIA,” vol. 12, no. 1, pp. 69–76, 2025, doi: 10.25126/jtiik.2025128860.

V. P. Carolina, E. Utami, and A. Yaqin, “Riset Jurnal Literatur: Morfologi Stemming Enhance Confix Stripping, Sastrawi Dan Tala Pada Bahasa Daerah Melayu-Ambon,” Journal homepage: Journal of Electrical Engineering and Computer (JEECOM), vol. xx, No. xx, pp. 186–194, Apr. 2024, doi: 10.33650/jeecom. v4i2.

R. Catelli, S. Pelosi, and M. Esposito, “Lexicon-Based vs. Bert-Based Sentiment Analysis: A Comparative Study in Italian,” Electronics (Switzerland), vol. 11, no. 3, Feb. 2022, doi: 10.3390/electronics11030374.

Agung Teguh Wibowo Amais and Adi Susilo, “Principal Component Analysis-Based Data Clustering for Labeling of Level Damage Sector in Post-Natural Disasters,” vol. XX, 2017, doi: 10.1109/ACCESS.2023.3275852.

A. Afda, “Analisis Dokumen Menggunakan Metode TF-IDF,” Jurnal Ekonomi Manajemen dan Informasi (JEMSI), vol. 5, pp. 466–169, Mar. 2024, doi: 10.31933/jemsi.v5i5.

S. M and Viera, “Cohen’s Kappa Coefficient as a Performance Measure for Feature Selection,” International Conference on Fuzzy Systems (FUZZ-IEEE 2010), Jul. 2010, doi: 978-1-4244-8126-2.

C. A. Nurhaliza Agustina, R. Novita, Mustakim, and N. E. Rozanda, “The Implementation of TF-IDF and Word2Vec on Booster Vaccine Sentiment Analysis Using Support Vector Machine Algorithm,” in Procedia Computer Science, Elsevier B.V., 2024, pp. 156–163. doi: 10.1016/j.procs.2024.02.162.

P. Guleria, J. Frnda, and P. N. Srinivasu, “NLP-based text classification using TF-IDF enabled fine-tuned long short-term memory: An empirical analysis,” Array, vol. 27, Sep. 2025, doi: 10.1016/j.array.2025.100467.

J. R. Landis and G. G. Koch, “An Application of Hierarchical Kappa-type Statistics in the Assessment of Majority Agreement among Multiple Observers,” Jun. 1977. doi: https://doi.org/10.2307/2529786.

R. Zwick, “Another Look at Interrater Agreement,” Psychol. Bull., vol. 103, no. 3, pp. 374–378, 1988, doi: 10.1037/0033-2909.103.3.374.

D. Banerjee, T. A. Taffa, and R. Usbeck, “Best Practices in AI and Data Science Models Evaluation,” in Lecture Notes in Informatics (LNI), Proceedings - Series of the Gesellschaft fur Informatik (GI), Gesellschaft fur Informatik (GI), 2025, pp. 1211–1219. doi: 10.18420/inf2025_105.

M. Tella, M. Ahmed Usman, and K. Ibrahim Musa, “A Systematic Analysis of Performance Evaluation Metrics in Machine Learning Models,” INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN APPLIED SCIENCE (IJRIAS), vol. XI, pp. 834–840, Jan. 2026, doi: 10.51584/IJRIAS.


Dimensions, PlumX, and Google Scholar Metrics

10.33650/jeecom.v8i1.16845


Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Laksmita Dewi Supraba, Andi Sunyoto, Setyo N

 
This work is licensed under a Creative Commons Attribution License (CC BY-SA 4.0)

Journal of Electrical Engineering and Computer (JEECOM)
Published by LP3M Nurul Jadid University, Indonesia, Probolinggo, East Java, Indonesia.