Sentiment Analysis of AI-Driven Job Automation in Indonesia: Integrating LSTM, BERTopic, and Time-Series Forecasting for Job Displacement Risk Prediction
DOI:
https://doi.org/10.30871/jaic.v10i2.12335Keywords:
Sentiment Analysis, Long Short-Term Memory, BERTopic, Job Automation, Job Displacement, Artificial IntelligenceAbstract
The rapid advancement of artificial intelligence (AI) has intensified public concerns regarding job automation and potential workforce displacement. While previous studies often examine sentiment, topic modeling, or temporal trends separately, this study integrates sentiment classification, topic modeling, and time-series forecasting to provide a comprehensive analysis of public perceptions in Indonesia. From an initial collection of 1.026 tweets, 966 validated Indonesian-language tweets from Twitter/X collected between 2024 and 2026 were retained for analysis. Sentiment labeling was conducted using a weakly supervised lexicon-based approach, followed by classification with a Long Short-Term Memory (LSTM) model. The model achieved 72% accuracy with a weighted F1-score of 0.72 and demonstrated strong performance in detecting negative sentiment, achieving a recall of 0.83. BERTopic modeling revealed dominant concerns related to job replacement, automation risks, vulnerable professions, and skill adaptation in the digital era. Furthermore, ARIMA-based time-series forecasting indicates that negative sentiment trends are likely to persist in the near future. This study contributes methodologically by integrating deep learning, topic modeling, and temporal forecasting within a unified framework to better understand evolving public risk perceptions of AI-driven job automation in Indonesia.
Downloads
References
[1] Izzatul Mula and Auliya Ristiani, “Transformasi Struktur Pekerjaan dan Kebutuhan Keterampilan di Era Teknologi AI dan Otomatisasi di Pasar Global,” Nian Tana Sikka : Jurnal ilmiah Mahasiswa, vol. 3, no. 1, pp. 155–167, Jan. 2025, doi: 10.59603/niantanasikka.v3i1.665.
[2] R. Putra, Sularno, and Zulfahmi, “Analisis Dampak Kecerdasan Buatan terhadap Transformasi Lapangan Kerja: Studi Literatur Sistematis,” JISKA: Jurnal Sistem Informasi dan Informatika, vol. 3, no. 2, pp. 70–74, Jul. 2025. [Online]. Available: http://jurnal.unidha.ac.id/index.php/jiska
[3] L. O. Lukmana, “Analisis Sentimen Terhadap Ulasan Pengguna Aplikasi Threads Instagram di Playstore Menggunakan Algoritma Naive Bayes,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, no. 2, Apr. 2025, doi: 10.23960/jitet.v13i2.6250.
[4] A. C. N. Rosyadi, Muhammad Athoillah, and Fenny Fitriani, “Analisis Sentimen Pengguna Twitter Mengenai Kotak Kosong di Pilkada Indonesia Tahun 2024 Menggunakan Algoritma LSTM,” Komputika : Jurnal Sistem Komputer, vol. 14, no. 2, pp. 193–202, Nov. 2025, doi: 10.34010/komputika.v14i2.16976.
[5] I K. T. Mertayasa and I D. M. B. A. Darmawan, “Pemodelan Topik Pada Ulasan Hotel Menggunakan Metode BERTopic Dengan Prosedur c-TF-IDF,” Jurnal Nasional Teknologi Informasi dan Aplikasinya (JNATIA), vol. 1, no. 1, pp. 307–316, Nov. 2022.
[6] D. Ayu Rezaldi, “PRISMA, Prosiding Seminar Nasional Matematika Peramalan Metode ARIMA Data Saham PT. Telekomunikasi Indonesia,” Peramalan Metode ARIMA Data Saham PT. Telekomunikasi Indonesia. PRISMA, Prosiding Seminar Nasional Matematika, vol. 4, pp. 611–620, 2021, [Online]. Available: https://journal.unnes.ac.id/sju/index.php/prisma/
[7] P. Rahmadani Panggabean and H. Al-Kausar Aidilof, “Sentiment Analysis of Public Comments on X Social Media Related to Israeli Product Boycotts Using The Long Short-Term Memory (LSTM) Method,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[8] A. Rizky Gunawan, R. Faticha, and A. Aziza, “Sentiment Analysis Using LSTM Algorithm Regarding Grab Application Services in Indonesia,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[9] I. Amelia et al., “Analisis Sentimen Opini Publik Terhadap Pengambil Alihan TMII Oleh Pemerintah dengan Algoritma Naïve Bayes.” [Online]. Available: https://journals.upi-yai.ac.id/index.php/ikraith-informatika/issue/archive
[10] M. U. Albab, Y. K. P., and M. N. Fawaiq, “Optimization of the Stemming Technique on Text Preprocessing President 3 Periods Topic,” Jurnal Transformatika, vol. 20, no. 2, pp. 1–12, Jan. 2023, doi: 10.26623/transformatika.v20i2.5374.
[11] S. Jessica Angelina, A. Bijaksana Putra Negara, H. Muhardi, J. H. Nawawi, and K. Barat, “Analisis Pengaruh Penerapan Stopword Removal Pada Performa Klasifikasi Sentimen Tweet Bahasa Indonesia Analyzing The Impact Of Applying Stopword Removal On Indonesian Tweet Sentiment Classification,” vol. 02, no. 1, 2023, doi: 10.26418/juara.v2i1.69680.
[12] A. S. Paramita and J. Jusak, “Fine-Grained Sentiment Analysis Approach on Customer Reviews Based on Aspect-Level Emotion Detection,” Journal of Applied Data Sciences, vol. 6, no. 3, pp. 2235–2247, Jul. 2025, doi: 10.47738/jads.v6i3.964.
[13] R. Wajhillah and A. Wibowo, “Information Retrieval Pemetaan Peta Jalan Penelitian Perguruan Tinggi Berbasis Dokumen Publikasi Ilmiah Dosen,” 2021. [Online]. Available: http://jurnal.bsi.ac.id/index.php/larik
[14] K. S. Witanto, N. A. Sanjaya ER, A. A. I. N. Eka Karyawati, I. G. A. G. A. Kadyanan, I. K. G. Suhartana, and L. G. Astuti, “Implementasi LSTM pada Analisis Sentimen Review Film Menggunakan Adam dan RMSprop Optimizer,” Jurnal Elektronik Ilmu Komputer Udayana, vol. 10, no. 4, pp. 351–362, May 2022.
[15] J. Cahyani, S. Mujahidin, and T. P. Fiqar, “Implementasi Metode Long Short Term Memory (LSTM) untuk Memprediksi Harga Bahan Pokok Nasional,” Jurnal Sistem dan Teknologi Informasi (JustIN), vol. 11, no. 2, p. 346, Jul. 2023, doi: 10.26418/justin.v11i2.57395.
[16] W. Wahyuni, T. P. Lestari, M. Apriliana, and R. Gumelta, “Implementation of BERTopic for Topic Modeling Analysis of the Free Nutritious Meal Program Based on YouTube Comments,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[17] S. V Kedar and S. Kadam, “Stock Market Increase and Decrease using Twitter Sentiment Analysis and ARIMA Model,” 2021.
[18] Y. Saputri, F. Syaki, and N. Hadinata, “Sentiment Analysis of Trending Topics on Social Media X Using Natural Language Processing and LSTM,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[19] A. Rachmadana Ismail, R. Bagus, F. Hakim, and R. Artikel, “Implementasi Lexicon Based Untuk Analisis Sentimen Dalam Mengetahui Trend Wisata Pantai Di DI Yogyakarta Berdasarkan Data Twitter P-ISSN E-ISSN,” 2023.
[20] H. Meliana Pratama, I. Lanang Wijayakusuma, and R. S. Widiastuti, “Comparison of Online Gambling Promotion Detection Performance Using DistilBERT and DeBERTa Models,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[21] C. K. N. Paputungan and A. Jacobus, “Sentiment Analysis of Social Media Users Using Long-Short
Term Memory Method Analisis Sentimen Pengguna Sosial Media Menggunakan Metode Long Short Term Memory,” Jurnal Teknik Elektro dan Komputer, vol. 10, no. 2.
[22] M. M. Gazali and H. Setiawan, “Penerapan Model ARIMA untuk Meramalkan Harga Pembukaan Harian Saham PT. Bank Central Asia Tbk,” Digital
Transformation Technology, vol. 5, no. 1, pp. 278–289, Jul. 2025, doi: 10.47709/digitech.v5i1.6129.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Valencia Elcheiana Irawan, Adi Suryaputra Paramita
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
