Analisis Sentimen Web Novel Menggunakan Metode Latent Dirichlet Allocation (LDA): Study Kasus Komentar Novel Harry Potter

Dewi Rosmala; Ryan Cahyadi N

doi:10.61132/merkurius.v2i2.74

Authors

Dewi Rosmala Institut Teknologi Nasional Bandung
Ryan Cahyadi N Institut Teknologi Nasional Bandung

DOI:

https://doi.org/10.61132/merkurius.v2i2.74

Keywords:

web novel, sentiment analysis, Latent Dirichlet Allocation (LDA), user comments, sentiment patterns

Abstract

Web novels have gained popularity in recent years as a form of literature that is published and consumed online via specialized platforms. User generated comments and reviews play an important role in the web novel platform, providing valuable insight into reader sentiment and feedback. Manually analyzing sentiment from a large number ofcomments would be very time consuming, an efficient automated approach was required. This study uses the Latent Dirichlet Allocation (LDA) method to identify sentiment patterns (positive, negative, neutral) in user comments on web novels and analyze their distribution as a whole. LDA, originally designed for topic modeling, has proven effective in sentiment analysis, helping to group comments into relevant topics and uncover general sentiments related to each topic. This study aims to use the LDA method to identify sentiment patterns (positive, negative, or neutral) in user comments on web novels and analyze the distribution of sentiment as a whole. The results show the effectiveness of LDA in sentiment analysis, achieving quite good results, with 72% accuracy, 80% precision, 72% recall, and 65% F1 score.

References

Akhmad, E. P. A., & Prawirosastro, C. L. (2021). Pemodelan Topik Menggunakan Latent Dirichlet Allocation Dan Pachinko Allocation Model Untuk Ekstraksi Berita Saham Online.

Bashri, M. F. A. (2017). Analisis sentimen menggunakan latent dirichlet allocation dan visualisasi topic polarity wordcloud. Semarang: Universitas Diponegoro.

Dheanis, K., Salsabila, A., Trianasari, N., Artikel, R., Kunci, K., & Konsumen, P. (2021). Jurnal Teknologi dan Manajemen Informatika Analisis Persepsi Produk Kosmetik Menggunakan Metode Sentiment Analysis Dan Topic Modeling (Studi Kasus: Laneige Water Sleeping Mask) Info Artikel ABSTRAK. Jurnal Teknologi Dan Manajemen Informatika, 7(1), 1–9. http://http//jurnal.unmer.ac.id/index.php/jtmi

Endriani, D. (2022). Analisis topic modelling mengenai pemberlakuan pembatasan kegiatan masyarakat menggunakan latent direchlet allocation (LDA). Universitas Islam Indonesia, 1–79.

Febrianta, M. Y., Widiyanesti, S., & Ramadhan, S. R. (2021). Analisis Ulasan Indie Video Game Lokal pada Steam Menggunakan Analisis Sentimen dan Pemodelan Topik Berbasis Latent Dirichlet Allocation. Journal of Animation and Games Studies, 7(2), 117–144. https://doi.org/10.24821/jags.v7i2.5162

Firdaus, A., & Firdaus, W. I. (2021). Text Mining Dan Pola Algoritma Dalam Penyelesaian Masalah Informasi : (Sebuah Ulasan). Jurnal JUPITER, 13(1), 66.

Habibi, M., Priadana, A., Saputra, A. B., & Cahyo, P. W. (2021). Topic Modelling of Germas Related Content on Instagram Using Latent Dirichlet Allocation (LDA). 34(Ahms 2020), 260–264. https://doi.org/10.2991/ahsr.k.210127.060

Isah, H., Trundle, P., & Neagu, D. (2014). Social media analysis for product safety using text mining and sentiment analysis. 2014 14th UK Workshop on Computational Intelligence, UKCI 2014 - Proceedings. https://doi.org/10.1109/UKCI.2014.6930158

Kabiru, I. N., & Sari, P. K. (2019). Analisa Konten Media Sosial E-commerce Pada Instagram Menggunakan Metode Sentiment Analysis Dan Lda-based Topic Modeling (studi Kasus: Shopee Indonesia). EProceedings of Management, 6(1), 12–19. https://openlibrarypublications.telkomuniversity.ac.id/index.php/management/article/view/8498

Luvian chisni chilmi, M. (2021). Latent dirichlet allocation (LDA) untuk mengetahui topik pembicaraan warganet twitter tentang omnibus law. Universitas Islam Negeri Syarif Hidayatullah, 1–131.

Nabilah, S. (2022). SKRIPSI Syauqatun Nabilah 11170940000052.

Nurdiansyah, Y., Rahman, F., & Pandunata, P. (2021). Analisis Sentimen Opini Publik Terhadap Undang-Undang Cipta Kerja pada Twitter Menggunakan Metode Naive Bayes Classifier. Prosiding Seminar Nasional Sains Teknologi Dan Inovasi Indonesia (SENASTINDO), 3(November), 201–212. https://doi.org/10.54706/senastindo.v3.2021.158

Puspita, B. H., Muhajir, M., & Aliady, H. (2020). Topic Modeling Using Latent Dirichlet Allocation (LDA) and Sentiment Analysis for Marketing Planning Tiket.com. 474(Isstec 2019), 16–22. https://doi.org/10.2991/assehr.k.201010.004

Putri, E. P. (2022). Implementasi Latent Dirichlet Allocation (Lda) Untuk Pemodelan Topik Faktor Perceraian.

Rachman, F. F., & Pramana, S. (2020). Analisis Sentimen Pro dan Kontra Masyarakat Indonesia tentang Vaksin COVID-19 pada Media Sosial Twitter. Health Information Management Journal, 8(2), 100–109. https://inohim.esaunggul.ac.id/index.php/INO/article/view/223/175

Ramadandi, R. (2021). Pemodelan Topik Menggunakan Metode Latent Dirichlet Allocation dan GIBBS Sampling. 74–79.

Susanto, I. K. (2021). Analisis Sentimen dan Topic Modelling Pada Pembelajaran Online di Indonesia Melalui Twitter. JOINTECS (Journal of Information Technology and Computer Science), 6(2), 85. https://doi.org/10.31328/jointecs.v6i2.2350

Tresnasari, N. A., Adji, T. B., & Permanasari, A. E. (2020). Social-Child-Case Document Clustering based on Topic Modeling using Latent Dirichlet Allocation. IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 14(2), 179. https://doi.org/10.22146/ijccs.54507

Valente Ferreira, J. C., Ribeiro Furtado, T., David Regis, R. D., Rodrigues Diniz, G., Gonçalves, P., & da Silva Castelo Tavares, V. P. (2023). Anime clustering for automatic classification and configuration of demographics. Cuadernos.Info, 54, 67–94. https://doi.org/10.7764/cdi.54.53193