Audience Responses Toward Digital Film Promotion on Youtube: A Study of Dilan ITB 1997 Trailer Comments

Mufidatul Azmi; Nidrah

doi:10.59890/ijaamr.v4i5.221

Authors

Mufidatul Azmi Universitas Negeri Makassar
Nidrah Universitas Negeri Makassar

DOI:

https://doi.org/10.59890/ijaamr.v4i5.221

Keywords:

Sentiment Analysis, Topic Modeling, Youtube Comments, e-WOM, Digital Film Promotion

Abstract

This study analyzes audience responses toward the Dilan ITB 1997 movie trailer on YouTube using IndoBERT sentiment analysis and Latent Dirichlet Allocation (LDA) topic modeling. The research aims to understand audience perceptions regarding character suitability, castins decisions, and audience responses toward digital film promotion. A total of 3,519 YouTube comments were collected through web scraping using Python in Google Colaboratory. The comments were processed through text preprocessing stages and classified into positive, negative, and neutral sentiments using the IndoBERT pretrained model. Furthermore, LDA topic modeling was applied to identify dominant discussion themes. The results indicate that negative sentiment dominated audience responses, mainly related to character suitability, casting decisions, and comparisons between previous and current portrayals of the characters in the movie trailer

References

Amien, M., & Gunawan, G. F. (2024). BERT dan Bahasa Indonesia : Studi tentang Efektivitas Model NLP Berbasis Transformer. ELANG: Journal of Interdiciplinary Research.

Buana, U. M., Raya, J., Rw, Sel, M., Kembangan, K., Khusus, D., & Jakarta, I. (2023). Analisis Topik dan Perbandingan Klasifikasi pada Kolom Komentar Video Youtube Edukasi Indonesia Menggunakan Pendekatan Latent Dirichlet Allocation Albert. Journal on Education, 05(03), 7418–7429.

Cici Suhaeni, Mualifah, L. N. A., & Wijayanto, H. (2025). LDA Topic Modeling Analysis of Public Discourse on Indonesia’s Free Nutritious Meals Program (MBG). IJID (International Journal on Informatics for Development), 14(1), 587–600. https://doi.org/10.14421/ijid.2025.5211

Gracia Ginting, A., Ezra Sipayung, D., Marbun, R., & Hasanah Harahap, S. (2024). Analisis Film Dilan 1990 Karya Pidi Baiq Menggunakan Pendekatan Mimetik. Jurnal Bastra, 9(3), 487–493. https://doi.org/10.26499/jk.

Gupta, S. (2023). The Impact Of E-Wom On Users’ Attitudes Toward Over-The-Top (Ott) Streaming Video Content And Its Subscription Intention. Article history : The year-on-year proliferation of the OTT industry in India has proved that OTTs are the most sought-af. International Journal of Professional Business Review, 8(2), 1–22. https://doi.org/https://doi.org/10.26668/businessreview/2023.v8i2.1046

Le, T. M., Lai, M. D., Nguyen, T. H., & Le, B. N. (2025). Understanding the Effect of Product Reviews on YouTube on Consumers’ Intention to Purchase Electronic Devices. SAGE Open. https://doi.org/10.1177/21582440251381530

Liu, H., & Jayawardhena, C. (2024). Electronic Word of Mouth 2.0 (eWOM 2.0): The Evolution of eWOM Research in the New Age. Journal of Business Research, 176. https://doi.org/10.1016/j.jbures.2024.000912

Nguyen, L. T., Chansanam, W., Hunsapun, N., Chaichuay, V., Kanyacome, S., Takhom, A., Jaroenruen, Y., & Li, C. (2024). Evaluating the Performance of Topic Modeling Techniques for Bibliometric Analysis Research: An LDA-based Approach. HighTech and Innovation Journal, 5(2), 312–330. https://doi.org/10.28991/HIJ-2024-05-02-07

Purnomo, T. D., Sutopo, J., & History, A. (2024). Comparison Of Pre-Trained Bert-Based Transformer Models For Regional. International Journal Science and Technology, 3(3), 11–21.

Retno, B., Sugiardi, S., & Bormasa, M. F. (2024). Consumer Sentiment Analysis in Continuous Marketing. Jurnal Ilmiah Manajemen Kesatuan, 12(6), 2517–2526. https://doi.org/10.37641/jimkes.v12i6.2991

Royani, N., Widodo, C. E., & Warsito, B. (2023). Topic Modelling Latent Dirichlet Allocation untuk Klasifikasi Komentar pada Layanan Streaming Platform. Jurnal Sains Dan Teknologi, 12(3), 815–822.

Sadiku, M. N. O., Kotteti, C. M. M., & Sadiku, J. O. (2024). Social media in entertainment. International Journal of Multidiciplinary Research and Growth Evaluation, 137–141.

Sayarizki, P. (2024). Implementation of IndoBERT for Sentiment Analysis of Indonesian Presidential Candidates. Ind. Journal on Computing, 9(2), 61–72.

Shaalan, A., Liu, H., & Jayawardhena, C. (2022). The impact of electronic word-of-mouth (eWOM) on consumer behaviours. In The SAGE handbook of digital marketing (pp. 136–158). Sage Publications. https://doi.org/10.4135/9781529782509.n9

Shah, D., & Parekh, M. (2023). From YouTube comments to insights: A sentiment analysis of opinions on productivity tools. International Journal for Research in Applied Science and Engineering Technology, 11(8). https://doi.org/10.22214/ijraset.2023.55579

Sri, B., Deepak, S., Rajiv, N. A., Praneeth, P., & Srikanth, S. (2024). Youtube Comments Extraction and Sentiment Analysis Using NLP. International Journal of Creative Research Thoughts, 12(4), 430–435.

Tarnovskaya, V. (2025). Audience Engagement on YouTube: A Merge of Consumer and Media Engagement. Proceedings of the 12th European Conference on Social Media. https://doi.org/10.34190/ecsm.12.1.3282

Tsalisa, S., & Setiyarini, T. (2025). Pengaruh E-Wom (Electronic Word Of Mouth) Di Media Sosial Terhadap. Jurnal Review Pendidikan Dan Pengajaran, 8(2008), 8019–8025.

Yan, Y. (2023). Research on Movie Trailers ’ Effectiveness in Attracting Audiences and Enhancing Marketing Strategies. Dean & Francis, 137–141.

Zamakhsyari, F., Suhana, R., Ramadhani, I., & Santoso, D. P. (2026). Sentiment Analysis of YouTube Comments for the Jumbo Movie Trailer Using IndoBERT. Smart Techno (Smart Technology, Informatic, Technopreneurship), 08(01), 142–150. https://doi.org/10.59356/smart-techno.v8i1.198