Aspect-Based Sentiment Analysis Using Latent Dirichlet Allocation (LDA) and DistilBERT on Threads App Reviews

Authors

  • Andreas Noprianto Kambayo Kambayo Informatic Department Universitas Kristen Immanuel
  • Sunneng Sandino Berutu
  • Jatmika Jatmika
  • Aristophane Nshimiyimana

DOI:

https://doi.org/10.61179/infact.v9i01.707

Keywords:

Threads, Aspect-Based Sentiment Analysis, DistilBERT, Latent Dirichlet Allocation

Abstract

Threads is a social media application that offers news services and user interaction, integrated with Instagram. Unlike other platforms, Threads does not have features like direct messaging (DM), trending topics, or advertisements. To understand users' opinions about this app, a sentiment analysis based on aspects was conducted on Threads reviews. The steps involved include applying web scraping techniques to collect reviews data from the Play Store. Aspect categories were identified using the Latent Dirichlet Allocation (LDA) algorithm. Sentiment labeling was then performed for positive and negative categories using the DistilBERT method. The results show that the LDA algorithm identified three aspects: Usage and Integration (with 3.147 positive and 8.173 negative reviews), Features and Comparisons (with 1.108 positive and 1.709 negative reviews), and User Experience and Satisfaction (with 3.529 positive and 2.208 negative reviews). The sentiment analysis results indicated 7,784 positive reviews and 12,090 negative reviews. Model performance evaluation using the Confusion Matrix showed an accuracy of 96.71%, precision of 97.24%, recall of 94.48%, and F1-score of 95.84%. Evaluation was also conducted for each aspect, with an accuracy of 96.99%, precision of 96.60%, recall of 92.85%, and F1-score of 94.69% for the Usage and Integration aspect; accuracy of 95.74%, precision of 94.11%, recall of 95.23%, and F1-score of 94.67% for the Features and Comparisons aspect; and accuracy of 96.74%, precision of 95.83%, recall of 99.06%, and F1-score of 97.42% for the User Experience and Satisfaction aspect.

References

A. G. Gani, “Pengenalan Teknologi Internet Serta Dampaknya,” JSI (Jurnal Sistem Informasi), vol. 2, no. 2, pp. 71-86, 2015, doi: https://doi.org/10.35968/jsi.v2i2.49.

S. R. Yustihan, P. P. Adikara, and I. Indriati, “Analisis Sentimen Berbasis Aspek Terhadap Data Ulasan Rumah Makan Menggunakan Metode Support Vector Machine (SVM),” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 5, no. 3, pp. 1017-1023, Maret 2021, doi: https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/8710.

M. Widiansyah, F. F. Az-Zahra, and A. Pambudi, “Fine-Tunning Model IndoBERT (Indonesian Bidirectional Encoder Representations from Transformers) Untuk Analisis Sentimen Berbasis Aspek Pada Aplikasi M-Paspor," Journal of Informatic Engineering (JOUTICA), vol. 9, no. 2, pp. 184-195, September 2024, doi: https://doi.org/10.30736/informatika.v9i2.1310.

S. Roiqoh, and B. Zaman, “Analisis Sentimen Berbasis Aspek Ulasan Aplikasi Mobile JKN dengan Lexicon Based dan Naïve Bayes,” Jurnal Media Informatika Budidarma, vol. 7, no. 3, pp. 1582-1592, Juli 2023, doi: https://doi.org/10.30865/mib.v7i3.6194.

M. Y. Febrianta, S. Widiyanesti, and S. R. Ramadhan,”" Analisis Ulasan Indie Video Game Lokal pada Steam Menggunakan Analisis Sentimen dan Pemodelan Topik Berbasis Latent Dirichlet Allocation,” Journal of Animation & Games Studies, vol. 7, no. 2, pp. 117-144, Oktober 2021, doi: https://doi.org/10.24821/jags.v7i2.5162.

E. Puspita, D. F. Shiddieq, and F. F. Roji, Pemodelan Topik pada Media Berita Online Menggunakan Latent Dirichlet Allocation (Studi Kasus Merek Somethinc),” Institut Riset dan Publikasi Indonesia (IRPI), MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 4, no. 2, pp: 481-489, April 2024, doi: https://doi.org/10.57152/malcom.v4i2.1204.

N. R. A. Putri, T. Trimono, and A. T. Damaliana, “Sentiment Analysis on Digital Korlantas POLRI Application Reviews Using the Distilbert Model,” Journal of Renewable Energy, Electrical, and Computer Engineering, vol. 4, no. 2, pp. 83-89, September 2024, doi: https://doi.org/10.29103/jreece.v4i2.17197.

H. C. Morama, D. E. Ratnawati, and I. Arwani, “Analisis Sentimen berbasis Aspek terhadap Ulasan Hotel Tentrem Yogyakarta menggunakan Algoritma Random Forest Classifier,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 6, no. 4, pp. 1702-1708, April 2022, available: https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/10908. [9] W. Parasati, F. A. Bachtiar, and N. Y. Setiawan, “Analisis Sentimen Berbasis Aspek pada Ulasan Pelanggan Restoran Bakso President Malang dengan Metode Naïve Bayes Classifier,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 4, no. 4, pp. 1090-1099, April 2020, available: https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/7134.

F. A. J. Ayomi, and K. Evita, “Analisis Emosi Pada Media Sosial Twitter Menggunakan Multinomial Naïve Bayes dan Synthetic Minority Oversampling Technique,” KOMPUTA: Jurnal Ilmiah Komputer dan Informatika, vol. 12, no. 2, pp. 9-19, Oktober 2023, doi: https://doi.org/10.34010/komputa.v12i2.9454.

M. U. Albab, Y. Karuniawati. P, and M. N. Fawaiq, “Optimization of the Stemming Technique on Text preprocessing President 3 Periods Topic,” Jurnal TRANSFORMATIKA, vol. 20, no. 2, pp. 1-10, Januari 2023, available: https://journals.usm.ac.id/index.php/transformatika/.

R. Lamhot, “Implementasi Metode Generalized Vector Space Model Pada Aplikasi Information Retrieval untuk Pencarian Informasi Pada Kumpulan Dokumen Teknik Elektro Di UPT BPI LIPI,” J. Ilm. Komput. dan Inform. (KOMPUTA), 2014.

Y. Miftahuddin, J. Pardede, and R. Dewi, “Penerapan Algoritma Lemmatization pada Dokumen Bahasa Indonesia,” MIND Journal, vol. 3, no.2, pp. 47-56, Desember 2018, doi: https://doi.org/10.26760/mindjournal.v3i2.47-56.

K. R. Hilal, N. Y. Setiawan, and D. E. Ratnawati, “Analisis Sentimen Berbasis Aspek Untuk Pengguna PLN Mobile Pada Google Playstore Menggunakan Metode Support Vector Machine (SVM),” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol.8, no.7, pp. 1-13, Juli 2024, available: https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/13927.

Z. N. Muna, B. D. Setiawan, and R. S. Perdana, Penerapan Pemodelan Topik Komentar Melalui Media Sosial Twitter Menggunakan Latent Dirichlet Allocation (Studi Kasus: Pemerintah Kota Malang),” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 8, no. 7, pp. 1-10, 2024, available: https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/13979.

R. F. R. Pohan, D. E. Ratnawati, and I. Arwani, “Implementasi Algoritma Support Vector Machine dan Model Bag-of-Words dalam Analisis Sentimen mengenai PILKADA 2020 pada Pengguna Twitter,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 6, no. 10, pp. 4924-4931, Oktober 2022, available: https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/11715.

W. T. H. Putri, and R. Hendrowati, “Penggalian Teks Dengan Model Bag of Words Terhadap Data Twitter,” Jurnal Muara Sains, Teknologi, Kedokteran, dan Ilmu Kesehatan, vol. 2, no. 1, pp. 129-138, April 2018, available: https://www.journal.untar.ac.id/index.php/jmistki/article/view/1560/1389.

D. P. Santoso, and W. Wibowo, “Analisis Sentimen Ulasan Aplikasi Buzzbreak Menggunakan Metode Naïve Bayes Classifier pada Situs Google Play Store,” Jurnal Sains dan Seni ITS, vol. 11, no. 2, pp.190-196, 2022, doi: https://doi.org/10.12962/j23373520.v11i2.72534.

H. Apriyani, and K. Kurniati, “Perbandingan Metode Naïve Bayes Dan Support Vector Machine Dalam Klasifikasi Penyakit Diabetes Melitus,” Journal of Information Technology Ampera, vol. 1, no. 3, pp. 133-143, Desember 2020, doi: https://doi.org/10.51519/journalita.

S. Clara, D. L. Prianto, R. A. Habsi, E. F. Lumbantobing, and N. Chamidah, “Implementasi Seleksi Fitur Pada Algoritma Klasifikasi Machine Learning Untuk Prediksi Penghasilan Pada Adult Income Dataset,” Seminar Nasional Mahasiswa Ilmu Komputer dan Aplikasinya (SENAMIKA), vol.2, no.1 pp. 741-747, April 2021, available: https://conference.upnvj.ac.id/index.php/senamika/article/view/1417.

Downloads

Published

2025-03-17

How to Cite

[1]
A. N. K. Kambayo, S. S. Berutu, J. Jatmika, and A. Nshimiyimana, “Aspect-Based Sentiment Analysis Using Latent Dirichlet Allocation (LDA) and DistilBERT on Threads App Reviews”, IIJC, vol. 9, no. 01, pp. 25–34, Mar. 2025.

Issue

Vol. 9 No. 01 (2025): International Journal of Computers

Section

Articles

License

Copyright (c) 2025 Andreas Noprianto Kambayo Kambayo

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

<a rel="license" href="http://creativecommons.org/licenses/by/4.0/"><img alt="Lisensi Creative Commons" style="border-width:0" src="https://i.creativecommons.org/l/by/4.0/88x31.png" /></a><br />Ciptaan disebarluaskan di bawah <a rel="license" href="http://creativecommons.org/licenses/by/4.0/">Lisensi Creative Commons Atribusi 4.0 Internasional</a>.