Analisis Sentimen Publik Terhadap Enterprise Resource Planning (ERP) Di Media Sosial X Menggunakan Model Roberta Dan Twitbert
DOI:
https://doi.org/10.31598/sintechjournal.v8i2.1920Keywords:
sentiment analysis, erp, model transformer, roberta, twitbertAbstract
Enterprise Resource Planning (ERP) has become an essential part of organizational digital transformation, helping to integrate various business functions. However, public acceptance of ERP on social media often serves as a crucial indicator of its successful implementation. This study aims to analyze public sentiment toward ERP on the social media platform X using two deep learning-based natural language processing models, RoBERTa and TweetBERT. These models are used to classify sentiment into Positive, Negative, or Neutral categories, with the goal of gaining a deeper understanding of public views on ERP. In this study, data was collected from social media X with 700 data points using a crawling method to obtain a substantial number of posts related to ERP. The data was processed through several stages, including text preprocessing, tokenization, and model training. RoBERTa, known for its ability to deeply understand the context of text, was compared with TweetBERT, a model optimized for short texts such as tweets. Evaluation was conducted using accuracy, precision, recall, and F1-score metrics to assess the performance of both models. The results show that RoBERTa has an accuracy of 0.40, with the best precision for positive sentiment (0.91) and the highest recall for negative sentiment (0.76). However, RoBERTa struggles to recognize positive sentiment, with a recall of only 0.23. On the other hand, TweetBERT shows higher accuracy (0.76), with the best precision for positive sentiment (0.89) and the highest recall for neutral sentiment (0.86). Although TweetBERT is more effective in capturing positive and neutral sentiments, it struggles to identify negative sentiment (with a recall of 0.12). This study provides valuable insights for companies and stakeholders to better understand public perception of ERP and assists in planning more effective communication strategies. The research also opens opportunities for further development by using a larger dataset or combining other models to improve sentiment prediction accuracy.
References
[1] M. Meiryani, E. Fernando, S. P. Hendratno, K. Kriswanto, and S. Wifasari, ‘Enterprise Resource Planning Systems: The Business Backbone’, pp. 43–48, 2021, doi: 10.1145/3466029.3466049.
[2] Md. S. A. Chowdhury, M. T. Rahman, A. M. Shahabuddin, M. R. Hassan, and M. S. R. Chowdhury, ‘Implementation of Enterprise Resource Planning (ERP) in Bangladesh -Opportunities and Challenges’, International Journal of Business and Management, vol. 16, no. 11, p. 1, 2021, doi: 10.5539/ijbm.v16n11p1.
[3] S. AboAbdo, A. Aldhoiena, and H. Al-Amrib, ‘Implementing Enterprise Resource Planning ERP System in a Large Construction Company in KSA’, Procedia Comput Sci, vol. 164, pp. 463–470, 2019, doi: 10.1016/j.procs.2019.12.207.
[4] M. Rizki, S. Basuki, and Y. Azhar, ‘Implementasi Deep Learning Menggunakan Arsitektur Long Short Term Memory(LSTM) Untuk Prediksi Curah Hujan Kota Malang’, 2020, Universitas Muhammadiyah Malang. doi: 10.22219/repositor.v2i3.470.
[5] S. Syafrudin, R. A. Nugraha, K. Handayani, S. Linawati, and W. Gata, ‘Prediksi Status Pinjaman Bank dengan Deep Learning Neural Network’, 2021, Universitas Bina Sarana Informatika. doi: 10.31294/jtk.v7i2.10474.
[6] F. D. Pratama and H. D. Bhakti, ‘IMPLEMENTASI APLIKASI PREDIKSI KETEPATAN PEMBAYARAN CUSTOMER PERUSAHAAN DENGAN METODE DECISION TREE’, 2023, Universitas Muhammadiyah Gresik. doi: 10.30587/indexia.v5i01.5082.
[7] R. I. Tampubolon, ‘Business Improvement Strategy for Local ERP Companies in Indonesia: SWOT Method, Fuzzy AHP-TOPSIS’, Jurnal Penelitian Medan Agama, vol. 15, no. 1, p. 84, 2024, doi: 10.58836/jpma.v15i1.21173.
[8] W. R. Faranita and M. Si. Ir. E. Nugroho, ‘IMPLEMENTATION OF THE ENTERPRISE RESOURCE PLANNING (ERP) SYSTEM ON MICRO, SMALL AND MEDIUM ENTERPRISES (MSME) BUSINESS ACTORS’, JBTI Jurnal Bisnis Teori dan Implementasi, vol. 12, no. 2, pp. 86–93, 2021, doi: 10.18196/jbti.v12i2.12191.
[9] D. E. Prasetyo and A. F. Wijaya, ‘Information System Strategic Planning For Tourism Transportation Company Using Ward And Peppard Methodology’, INTENSIF Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi, vol. 5, no. 1, pp. 43–57, 2021, doi: 10.29407/intensif.v5i1.14609.
[10] G. P. Aulia, T. Widiharih, and I. T. Utami, ‘PENERAPAN TEXT MINING DAN FUZZY C-MEANS CLUSTERING UNTUK IDENTIFIKASI KELUHAN UTAMA PELANGGAN PDAM TIRTA MOEDAL KOTA SEMARANG’, Jurnal Gaussian, vol. 12, no. 1, pp. 126–135, 2022, doi: 10.14710/j.gauss.12.1.126-135.
[11] I. Salamah and S. Suroso, ‘Implementasi Algoritma Naive Bayes Terhadap Klasifikasi Jenis Pertanyaan Pada Perancangan Chatbot Untuk Aplikasi Penjualan Songket’, JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 8, no. 3, p. 1734, 2024, doi: 10.30865/mib.v8i3.7908.
[12] L. A. Palinkas, S. M. Horwitz, C. A. Green, J. P. Wisdom, N. Duan, and K. Hoagwood, ‘Purposeful Sampling for Qualitative Data Collection and Analysis in Mixed Method Implementation Research’, 2013, Springer Science+Business Media. doi: 10.1007/s10488-013-0528-y.
[13] M. Zubair, J. Ali, M. Alhussein, S. Hassan, K. Aurangzeb, and M. Umair, ‘An Improved Machine Learning-Driven Framework for Cryptocurrencies Price Prediction With Sentimental Cautioning’, IEEE Access, vol. 12, pp. 51395–51418, 2024, doi: 10.1109/access.2024.3367129.
[14] Y. Asri, W. N. Suliyanti, D. Kuswardani, and M. Fajri, ‘Pelabelan Otomatis Lexicon Vader dan KlasifikasAsri, Y., Suliyanti, W. N., Kuswardani, D., & Fajri, M. (2022). Pelabelan Otomatis Lexicon Vader dan Klasifikasi Naive Bayes dalam menganalisis sentimen data ulasan PLN Mobile. PETIR, 15(2), 264–275. https://’, Petir, vol. 15, no. 2, pp. 264–275, 2022.
[15] E. Lin, J. Sun, H. Chen, and M. H. Mahoor, ‘Data Quality Matters: Suicide Intention Detection on Social Media Posts Using a RoBERTa-CNN Model’, arXiv (Cornell University), 2024, doi: 10.48550/arxiv.2402.02262.
[16] M. Muffo and E. Bertino, ‘BERTino: an Italian DistilBERT model’, in Accademia University Press eBooks, Accademia University Press, 2020, pp. 317–322. doi: 10.4000/books.aaccademia.8748.
[17] J. Devlin, M. Chang, K. Lee, and K. Toutanova, ‘BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding’, arXiv (Cornell University), 2018, doi: 10.48550/arXiv.1810.04805.
[18] A. F. Hidayatullah, R. A. A. H. M. Apong, D. T. C. Lai, and A. Qazi, ‘Corpus creation and language identification for code-mixed Indonesian-Javanese-English Tweets’, PeerJ Comput Sci, vol. 9, 2023, doi: 10.7717/peerj-cs.1312.
[19] T. Wu, Y. Wang, and N. Quach, ‘Advancements in Natural Language Processing: Exploring Transformer-Based Architectures for Text Understanding’, 2025, doi: 10.48550/ARXIV.2503.20227.
[20] S. Shevira, I. M. A. D. Suarjaya, and P. W. Buana, ‘Pengaruh Kombinasi dan Urutan Pre-Processing pada Tweets Bahasa Indonesia’, JITTER Jurnal Ilmiah Teknologi dan Komputer, vol. 3, no. 2, p. 1074, 2022, doi: 10.24843/jtrti.2022.v03.i02.p06.
[21] H. GhorbanTanhaei, P. Boozary, S. Sheykhan, M. Rabiee, F. Rahmani, and I. Hosseini, ‘Predictive Analytics in Customer Behavior: Anticipating Trends and Preferences’, Results in Control and Optimization, p. 100462, 2024, doi: 10.1016/j.rico.2024.100462.
[22] R. S. Samir, ‘EfficientNet Algorithm for Classification of Different Types of Cancer’, arXiv (Cornell University), 2023, doi: 10.48550/arXiv.2304.08715.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Bery Agustianto, Ahmad Musyafa, Arya Adhyaksa Waskita
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
1.png)
