Analisis Sentimen Pengguna Media Sosial Terhadap Konten Virtual Idol Berbasis AI: Studi Kasus MAVE

Hashfi Shani; Yohanna Ria Laura Ambarita; Cici Sundari; Evta Indra

doi:10.56427/jcbd.v5i2.1008

Authors

Hashfi Shani Universitas Prima Indonesia
Yohanna Ria Laura Ambarita Universitas Prima Indonesia
Cici Sundari Universitas Prima Indonesia
Evta Indra Universitas Prima Indonesia

DOI:

https://doi.org/10.56427/jcbd.v5i2.1008

Keywords:

Analisis Sentimen, IndoBERT, Virtual Idol AI, Media Sosial, SERVQUAL

Abstract

Virtual idol berbasis kecerdasan buatan (Artificial Intelligence/AI) menjadi fenomena yang semakin berkembang dalam industri hiburan digital melalui berbagai platform media sosial. Meskipun interaksi pengguna terhadap virtual idol terus meningkat, penelitian yang mengintegrasikan analisis sentimen dan evaluasi kualitas layanan digital dalam konteks virtual idol berbasis AI masih relatif terbatas. Penelitian ini bertujuan menganalisis sentimen pengguna media sosial terhadap konten virtual idol AI MAVE menggunakan model IndoBERT Fine-Tuning serta mengevaluasi kualitas layanan menggunakan pendekatan SERVQUAL. Penelitian menerapkan metode mixed method dengan dua sumber data, yaitu 2,493 komentar YouTube yang dianalisis menggunakan IndoBERT Fine-Tuning dan data survei SERVQUAL dari 216 responden penggemar MAVE di Indonesia. Hasil analisis sentimen menunjukkan bahwa sentimen positif mendominasi sebesar 63.46%, diikuti sentimen netral sebesar 27.32%, dan sentimen negatif sebesar 9.23%. Hasil analisis SERVQUAL menunjukkan bahwa seluruh dimensi kualitas layanan memiliki kesenjangan negatif yang signifikan antara ekspektasi dan persepsi pengguna. Kebaruan penelitian ini terletak pada integrasi analisis sentimen berbasis IndoBERT Fine-Tuning dan evaluasi kualitas layanan SERVQUAL untuk memahami persepsi pengguna terhadap virtual idol berbasis AI. Temuan penelitian memberikan wawasan bagi pengembang virtual idol dalam meningkatkan kualitas layanan dan pengalaman pengguna pada ekosistem hiburan digital berbasis AI.

Downloads

Download data is not yet available.

References

[1] O. Peinado and M. Shim, “The intersection of ‘real’ and ‘reel’: An investigation of K-pop idol dual self-presentation, paid advertisements, and fan engagement,” Comput. Human Behav., vol. 161, p. 108414, Dec. 2024, doi: 10.1016/j.chb.2024.108414.

[2] V. M. Ngo, “Does ChatGPT change artificial intelligence-enabled marketing capability? Social media investigation of public sentiment and usage,” Glob. Media China, vol. 9, no. 1, pp. 101–125, Mar. 2024, doi: 10.1177/20594364241228880.

[3] B. Goswami, N. Bhavsar, S. A. Alzobidy, B. Lavanya, R. Udhayakumar, and K. Rajapandian, “Sentiment Analysis Using Natural Language Processing,” in Natural Language Processing for Software Engineering, Wiley, 2025, pp. 283–294. doi: 10.1002/9781394272464.ch20.

[4] M. F. Mubaraq and W. Maharani, “Sentiment Analysis on Twitter Social Media towards Climate Change on Indonesia Using IndoBERT Model,” J. MEDIA Inform. BUDIDARMA, vol. 6, no. 4, p. 2426, Oct. 2022, doi: 10.30865/mib.v6i4.4570.

[5] Ibadurrohman Irfan Fatani, “Twitter, Instagram, Youtube Speak: Understanding Sentiments on LRT Jabodebek Services via Inset Lexicon, IndoBERT and BERTopic Approaches,” J. Electr. Syst., vol. 20, no. 4s, pp. 1028–1035, Apr. 2024, doi: 10.52783/jes.2147.

[6] Teddy Oswari, Murniyati, Trityanti Yusnitasari, Nurasiah, and Seviyanti Wijay, “Sentiment Analysis of Indonesian YouTube Reviews About Lesbian, Gay, Bisexual, and Transgender (LGBT) using IndoBERT Fine Tuning,” Lontar Komput. J. Ilm. Teknol. Inf., vol. 15, no. 01, pp. 26–37, Oct. 2025, doi: 10.24843/LKJITI.2024.v15.i01.p03.

[7] Serly Setyani, “Multi Aspect Sentiment Analysis of Mutual Funds Investment App Bibit Using BERT Method,” Int. J. Inf. Commun. Technol., vol. 9, no. 1, pp. 44–56, Jul. 2023, doi: 10.21108/ijoict.v9i1.718.

[8] S. A. Putra and A. Wijaya, “ANALISIS SENTIMEN ARTIFICIAL INTELLIGENCE (AI) PADA MEDIA SOSIAL TWITTER MENGGUNAKAN METODE LEXICON BASED,” JuSiTik J. Sist. dan Teknol. Inf. Komun., vol. 7, no. 1, pp. 21–28, Dec. 2023, doi: 10.32524/jusitik.v7i1.1042.

[9] D. D. Albesta, M. L. Jonathan, M. Jawad, O. Hardiawan, and D. Suhartono, “The impact of sentiment analysis from user on Facebook to enhanced the service quality,” Int. J. Electr. Comput. Eng., vol. 11, no. 4, p. 3424, Aug. 2021, doi: 10.11591/ijece.v11i4.pp3424-3433.

[10] A. I. A. Rahim, M. I. Ibrahim, S.-L. Chua, and K. I. Musa, “Hospital Facebook Reviews Analysis Using a Machine Learning Sentiment Analyzer and Quality Classifier,” Healthcare, vol. 9, no. 12, p. 1679, Dec. 2021, doi: 10.3390/healthcare9121679.

[11] A. Kautsar, “Classification of Korean Drama Popularity Based on Ratings Using Naïve Bayes,” J. Comput. Digit. Bus., vol. 5, no. 1, pp. 23–30, Jan. 2026, doi: 10.56427/jcbd.v5i1.814.

[12] Y. C. Gucci, K. Y. S. Putri, and V. W. Sutjipto, “Analysis of Interpersonal Communication Patterns in K-POP Fans’ Parasocial Interactions,” J. Media,Culture Commun., no. 42, pp. 1–7, Feb. 2024, doi: 10.55529/jmcc.42.1.7.

[13] E. J. Kang, H. Kim, H. Kim, S. R. Fussell, and J. Kim, “Can Fans Build Parasocial Relationships through Idols’ Simulated Voice Messages?: A Study of AI Private Call Users’ Perceptions, Cognitions, and Behaviors,” Proc. ACM Human-Computer Interact., vol. 9, no. 2, pp. 1–31, May 2025, doi: 10.1145/3711111.

[14] N. M. P. Dewanggi and B. G. Septarini, “Impact of K-Pop Idol Dating Scandals on Fans’ Parasocial Relationships with Idols: Comparing Indonesian and South Korean Fans,” Psympathic J. Ilm. Psikol., vol. 12, no. 2, pp. 57–70, Dec. 2025, doi: 10.15575/psy.v12i2.41373.

[15] D. Arli, P. van Esch, and S. Weaven, “The Impact of SERVQUAL on Consumers’ Satisfaction, Loyalty, and Intention to Use Online Food Delivery Services,” J. Promot. Manag., vol. 30, no. 7, pp. 1159–1188, Oct. 2024, doi: 10.1080/10496491.2024.2372858.

[16] J. Schoonenboom and R. B. Johnson, “How to Construct a Mixed Methods Research Design,” KZfSS Kölner Zeitschrift für Soziologie und Sozialpsychologie, vol. 69, no. S2, pp. 107–131, Oct. 2017, doi: 10.1007/s11577-017-0454-1.

[17] M. Tavakol and R. Dennick, “Making sense of Cronbach’s alpha,” Int. J. Med. Educ., vol. 2, pp. 53–55, Jun. 2011, doi: 10.5116/ijme.4dfb.8dfd.