Indonesian Cross-Platform Sentiment Analysis: DANN Transfer from General Applications to TradingView

Muh. Rifqi Zulkifli; Purnawansyah; Herdianti Darwis

doi:10.56705/ijodas.v6i3.318

Authors

Muh. Rifqi Zulkifli Universitas Muslim Indonesia
Purnawansyah Universitas Muslim Indonesia
Herdianti Darwis Universitas Muslim Indonesia

DOI:

https://doi.org/10.56705/ijodas.v6i3.318

Keywords:

Domain adaptation; Indonesian sentiment analysis; Cross-platform transfer; DANN; Statistical validation.

Abstract

Introduction: Cross-platform sentiment analysis for Indonesian language presents significant challenges when adapting models from general applications to specialized domains. Domain Adversarial Neural Networks (DANN) offer promising solutions for transfer learning, yet their effectiveness for Indonesian language remains largely unexplored, particularly under extreme class imbalance conditions common in trading platforms. Methods: This study investigates DANN effectiveness for transferring sentiment analysis knowledge from four strategically selected source domains to TradingView trading platform. The research utilizes 5,990 Indonesian reviews after preprocessing from an initial 6,000 samples, with source domains showing 66.5% positive sentiment while target domain exhibits 85.1% positive sentiment, creating an 18.7% distribution gap. Four experimental approaches were compared with statistical validation across multiple random initializations: Source-Only training, Multi-Domain training, Limited Target training, and DANN implementation. Results: DANN demonstrates stable cross-platform adaptation, achieving 87.77% ± 0.97% accuracy with consistent performance across initializations, outperforming Source-Only baseline (87.10% ± 0.84%) and Multi-Domain approach (86.98% ± 0.64%). While Limited Target baseline achieves higher accuracy (88.10% ± 2.23%), its high variance poses deployment risks. A-distance analysis reveals substantial domain gaps (193.00 ± 1.06), with DANN's adversarial training achieving modest domain separation reduction (72.90% ± 8.81% domain discrimination accuracy). Conclusions: This research contributes the first systematic evaluation of DANN for Indonesian cross-platform sentiment analysis, demonstrating that deployment consistency outweighs peak accuracy for production environments. The findings provide practical value for Indonesian fintech startups requiring robust sentiment analysis with limited labeled data. Future work should explore multi-target adaptation and optimization strategies for diverse Indonesian business domains

Downloads

Download data is not yet available.

References

[1] E. Zuo, A. Aysa, M. Muhammat, Y. Zhao, and K. Ubul, “Context aware semantic adaptation network for cross domain implicit sentiment classification,” Sci. Rep., vol. 11, no. 1, pp. 1–14, 2021, doi: 10.1038/s41598-021-01385-1.

[2] R. Kusumaningrum, I. Z. Nisa, R. Jayanto, R. P. Nawangsari, and A. Wibowo, “Deep learning-based application for multilevel sentiment analysis of Indonesian hotel reviews,” Heliyon, vol. 9, no. 6, p. e17147, 2023, doi: 10.1016/j.heliyon.2023.e17147.

[3] M. HassanPour Zonoozi and V. Seydi, “A Survey on Adversarial Domain Adaptation,” Neural Process. Lett., vol. 55, no. 3, pp. 2429–2469, 2023, doi: 10.1007/s11063-022-10977-5.

[4] H. Jayadianti, W. Kaswidjanti, A. T. Utomo, S. Saifullah, F. A. Dwiyanto, and R. Drezewski, “Sentiment analysis of Indonesian reviews using fine-tuning IndoBERT and R-CNN,” Ilk. J. Ilm., vol. 14, no. 3, pp. 348–354, 2022, doi: 10.33096/ilkom.v14i3.1505.348-354.

[5] A. S. Ekakristi, A. F. Wicaksono, and R. Mahendra, “Intermediate-task transfer learning for Indonesian NLP tasks,” Nat. Lang. Process. J., vol. 12, no. May, p. 100161, 2025, doi: 10.1016/j.nlp.2025.100161.

[6] A. Romadhony, S. Al Faraby, R. Rismala, U. N. Wisesti, and A. Arifianto, “Sentiment Analysis on a Large Indonesian Product Review Dataset,” J. Inf. Syst. Eng. Bus. Intell., vol. 10, no. 1, pp. 167–178, 2024, doi: 10.20473/jisebi.10.1.167-178.

[7] Y. A. Singgalen, “Performance Analysis of IndoBERT for Sentiment Classification in Indonesian Hotel Review Data,” Artic. J. Inf. Syst. Res., vol. 6, no. 2, p. 978−988, 2025, doi: 10.47065/josh.v6i2.6505.

[8] I. Sel and D. Hanbay, “Efficient Adaptation: Enhancing Multilingual Models for Low-Resource Language Translation,” Mathematics, vol. 12, no. 19, 2024, doi: 10.3390/math12193149.

[9] L. N. Hayati, F. Y. Randana, and H. Darwis, “An In-depth Exploration of Sentiment Analysis on Hasanuddin Airport using Machine Learning Approaches,” J. RESTI, vol. 9, no. 2, pp. 195–208, 2025, doi: 10.29207/resti.v9i2.6253.

[10] C. H. Lin and U. Nuha, “Sentiment analysis of Indonesian datasets based on a hybrid deep-learning strategy,” J. Big Data, vol. 10, no. 1, 2023, doi: 10.1186/s40537-023-00782-9.

[11] H. Badr, N. Wanas, and M. Fayek, “Unsupervised Domain Adaptation via Weighted Sequential Discriminative Feature Learning for Sentiment Analysis,” Appl. Sci., vol. 14, no. 1, 2024, doi: 10.3390/app14010406.

[12] A. Sicilia, X. Zhao, and S. J. Hwang, “Domain adversarial neural networks for domain generalization: when it works and how to improve,” Mach. Learn., vol. 112, no. 7, pp. 2685–2721, 2023, doi: 10.1007/s10994-023-06324-x.

[13] H. Qin, J. Pan, J. Li, and F. Huang, “Improved Conditional Domain Adversarial Networks for Intelligent Transfer Fault Diagnosis,” Mathematics, vol. 12, no. 3, 2024, doi: 10.3390/math12030481.

[14] H. Wu and X. Shi, “Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis,” Proc. Annu. Meet. Assoc. Comput. Linguist., vol. 1, pp. 2438–2447, 2022, doi: 10.18653/v1/2022.acl-long.174.

[15] J. Yu, C. Gong, and R. Xia, “Cross-Domain Review Generation for Aspect-Based Sentiment Analysis,” Find. Assoc. Comput. Linguist. ACL-IJCNLP 2021, pp. 4767–4777, 2021, doi: 10.18653/v1/2021.findings-acl.421.

[16] M. Rostami, S. Narayanan, D. Bose, and A. Galstyan, “Domain Adaptation for Sentiment Analysis Using Robust Internal Representations,” Find. Assoc. Comput. Linguist. EMNLP 2023, pp. 11484–11498, 2023, doi: 10.18653/v1/2023.findings-emnlp.769.

[17] M. C. Hinojosa Lee, J. Braet, and J. Springael, “Performance Metrics for Multilabel Emotion Classification: Comparing Micro, Macro, and Weighted F1-Scores,” Appl. Sci., vol. 14, no. 21, 2024, doi: 10.3390/app14219863.

[18] N. Liu and J. Zhao, “A BERT-Based Aspect-Level Sentiment Analysis Algorithm for Cross-Domain Text,” Comput. Intell. Neurosci., vol. 2022, 2022, doi: 10.1155/2022/8726621.

[19] R. I. Perwira, V. A. Permadi, D. I. Purnamasari, and R. P. Agusdin, “Domain-Specific Fine-Tuning of IndoBERT for Aspect-Based Sentiment Analysis in Indonesian Travel User-Generated Content,” J. Inf. Syst. Eng. Bus. Intell., vol. 11, no. 1, pp. 30–40, 2025, doi: 10.20473/jisebi.11.1.30-40.

[20] A. Serlina, A. Rahim, and Arbansyah, “Comparative Analysis of Naïve Bayes Algorithm Performance in English and Indonesian Text Sentiment Classification on Duolingo Application in Playstore,” Teknika, vol. 14, no. 1, pp. 165–171, 2025, doi: 10.34148/teknika.v14i1.1207.

[21] G. Joshi et al., “Explainable Misinformation Detection Across Multiple Social Media Platforms,” IEEE Access, vol. 11, no. January, pp. 23634–23646, 2023, doi: 10.1109/ACCESS.2023.3251892.

[22] A. Rusli, “On the Applicability of Zero-Shot Cross-Lingual Transfer Learning for Sentiment Classification in Distant Language Pairs,” arXiv Prepr. arXiv2412., vol. 0, pp. 1243–1247, 2024

[23] H. Ahmadian, T. F. Abidin, H. Riza, and K. Muchtar, “Hybrid Models for Emotion Classification and Sentiment Analysis in Indonesian Language,” Appl. Comput. Intell. Soft Comput., vol. 2024, 2024, doi: 10.1155/2024/2826773.

[24] S. Dong and C. Liu, “Sentiment Classification for Financial Texts Based on Deep Learning,” Comput. Intell. Neurosci., vol. 2021, 2021, doi: 10.1155/2021/9524705.

[25] Z. Cao, Y. Zhou, A. Yang, and S. Peng, “Deep transfer learning mechanism for fine-grained cross-domain sentiment classification,” Conn. Sci., vol. 33, no. 4, pp. 911–928, 2021, doi: 10.1080/09540091.2021.1912711.

[26] H. Tang, Y. Mi, F. Xue, and Y. Cao, “Graph Domain Adversarial Transfer Network for Cross-Domain Sentiment Classification,” IEEE Access, vol. 9, pp. 33051–33060, 2021, doi: 10.1109/ACCESS.2021.3061139.

[27] J. Lyu, Z. Zhang, S. Chen, and X. Fan, “Global-Local Dynamic Adversarial Learning for Cross-Domain Sentiment Analysis,” Mathematics, vol. 11, no. 14, 2023, doi: 10.3390/math11143130.

[28] K. Alahmadi, S. Alharbi, J. Chen, and X. Wang, “Generalizing sentiment analysis: a review of progress, challenges, and emerging directions,” Soc. Netw. Anal. Min., vol. 15, no. 1, 2025, doi: 10.1007/s13278-025-01461-8.

[29] M. Ijaz, N. Anwar, M. Safran, S. Alfarhood, T. Sadad, and Imran, “Domain adaptive learning for multi realm sentiment classification on big data,” PLoS One, vol. 19, no. 4 April, pp. 1–28, 2024, doi: 10.1371/journal.pone.0297028.

[30] K. L. Tan, C. P. Lee, and K. M. Lim, “A Survey of Sentiment Analysis: Approaches, Datasets, and Future Research,” Appl. Sci., vol. 13, no. 7, 2023, doi: 10.3390/app13074550.