Utilization of Adaptive Machine Learning for Streaming Sentiment Analysis: The Effects of Batch and Drift Types
Received: 19 November 2025 | Revised: 13 December 2025, 30 December 2025, 1 January 2026, and 3 January 2026 | Accepted: 4 January 2026 | Online: 9 February 2026
Corresponding author: Sudianto Sudianto
Abstract
The changing data patterns that continue to emerge from user reviews on digital platforms demand machine learning models to be able to adapt sustainably. This phenomenon, known as concept drift, can degrade accuracy if not handled appropriately. The study explores two adaptive learning approaches—Adaptive Random Forest (ARF) and Adaptive XGBoost (AXGB)—to classify sentiment on real-time data streams. The dataset used includes OVO reviews (2016–2025) and GoPay reviews (2023–2025) from the Google Play Store. After performing text cleanup, tokenization, stemming, and Term Frequency–Inverse Document Frequency (TF-IDF) representation, the data are streamed into two learning schemes: Big Batch Small Batch (BBSB), which combines large and small batches to detect changes more subtly, and N Drift Types Batch (NDTB), which adjusts batch sizes based on the number of drift types considered. The evaluation was carried out using accuracy metrics, computational time, and true positive rate in each sentiment category. The results showed that ARF provided the most stable performance with an average accuracy of 82%, whereas AXGB performed better in the BBSB configuration with an accuracy of 81% and faster training time. These findings confirm that both configurations can serve as practical frameworks for text stream learning and adaptive concept drift management.
Keywords:
adaptive learning, concept drift, data stream, batch streaming, sentiment analysisDownloads
References
G. J. Aguiar and A. Cano, "Enhancing Concept Drift Detection in Drifting and Imbalanced Data Streams through Meta-Learning," in 2023 IEEE International Conference on Big Data, Sorrento, Italy, 2023, pp. 2648–2657. DOI: https://doi.org/10.1109/BigData59044.2023.10386364
M. A. Shyaa, N. F. Ibrahim, Z. Zainol, R. Abdullah, M. Anbar, and L. Alzubaidi, "Evolving cybersecurity frontiers: A comprehensive survey on concept drift and feature dynamics aware machine and deep learning in intrusion detection systems," Engineering Applications of Artificial Intelligence, vol. 137, Nov. 2024, Art. no. 109143. DOI: https://doi.org/10.1016/j.engappai.2024.109143
B. Halstead et al., "Analyzing and repairing concept drift adaptation in data stream classification," Machine Learning, vol. 111, no. 10, pp. 3489–3523, Oct. 2022. DOI: https://doi.org/10.1007/s10994-021-05993-w
X. Jin and Y. Zhang, "Adaptive Random Forest with Dynamic Detectors for Evolving Data Stream Classification," in Proceedings of the 2023 9th International Conference on Computing and Artificial Intelligence, Tianjin, China, 2023, pp. 678–684. DOI: https://doi.org/10.1145/3594315.3594390
N. Abdulla, M. Demirci, and S. Özdemir, "Adaptive Learning on Fog-Cloud Collaborative Architecture for Stream Data Processing," in 2021 International Symposium on Networks, Computers and Communications, Dubai, United Arab Emirates, 2021, pp. 1–6. DOI: https://doi.org/10.1109/ISNCC52172.2021.9615824
A. O. AlQabbany and A. M. Azmi, "Measuring the Effectiveness of Adaptive Random Forest for Handling Concept Drift in Big Data Streams," Entropy, vol. 23, no. 7, July 2021, Art. no. 859. DOI: https://doi.org/10.3390/e23070859
Ł. Korycki and B. Krawczyk, "Adaptive Deep Forest for Online Learning from Drifting Data Streams." arXiv, Oct. 14, 2020.
M. G. Rahman and M. Z. Islam, "Adaptive Decision Forest: An incremental machine learning framework," Pattern Recognition, vol. 122, Feb. 2022, Art. no. 108345. DOI: https://doi.org/10.1016/j.patcog.2021.108345
L. Yang and A. Shami, "A Lightweight Concept Drift Detection and Adaptation Framework for IoT Data Streams," IEEE Internet of Things Magazine, vol. 4, no. 2, pp. 96–101, June 2021. DOI: https://doi.org/10.1109/IOTM.0001.2100012
D. Joshi and M. Shukla, "An Ensemble Approach to Improve the Performance of Real Time Data Stream Classification," Engineering, Technology & Applied Science Research, vol. 14, no. 6, pp. 17749–17754, Dec. 2024. DOI: https://doi.org/10.48084/etasr.8563
F. Ceschin, M. Botacin, H. M. Gomes, F. Pinagé, L. S. Oliveira, and A. Grégio, "Fast & Furious: On the modelling of malware detection as an evolving data stream," Expert Systems with Applications, vol. 212, Feb. 2023, Art. no. 118590. DOI: https://doi.org/10.1016/j.eswa.2022.118590
M. Badar, W. Nejdl, and M. Fisichella, "FAC-fed: Federated adaptation for fairness and concept drift aware stream classification," Machine Learning, vol. 112, no. 8, pp. 2761–2786, Aug. 2023. DOI: https://doi.org/10.1007/s10994-023-06360-7
E. Yu, J. Lu, B. Zhang, and G. Zhang, "Online Boosting Adaptive Learning under Concept Drift for Multistream Classification," Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 15, pp. 16522–16530, Mar. 2024. DOI: https://doi.org/10.1609/aaai.v38i15.29590
E. Yu, Y. Song, G. Zhang, and J. Lu, "Learn-to-adapt: Concept drift adaptation for hybrid multiple streams," Neurocomputing, vol. 496, pp. 121–130, July 2022. DOI: https://doi.org/10.1016/j.neucom.2022.05.025
V. Yelleti, "ROSFD: Robust Online Streaming Fraud Detection with Resilience to Concept Drift in Data Streams." arXiv, Apr. 14, 2025.
Y. Zhong, H. Yang, Y. Zhang, P. Li, and C. Ren, "Long short-term memory self-adapting online random forests for evolving data stream regression," Neurocomputing, vol. 457, pp. 265–276, Oct. 2021. DOI: https://doi.org/10.1016/j.neucom.2021.05.026
Z. Pang, J. Cen, and M. Yi, "Unsupervised concept drift detection method based on robust random cut forest," International Journal of Machine Learning and Cybernetics, vol. 14, no. 12, pp. 4207–4222, Dec. 2023. DOI: https://doi.org/10.1007/s13042-023-01890-x
F. Ridder, K.-H. Chen, and N. Alachiotis, "Accelerated Real-Time Classification of Evolving Data Streams using Adaptive Random Forests," in 2023 International Conference on Field Programmable Technology, Yokohama, Japan, 2023, pp. 232–237. DOI: https://doi.org/10.1109/ICFPT59805.2023.00031
M. A. Shyaa et al., "Enhanced Intrusion Detection with Data Stream Classification and Concept Drift Guided by the Incremental Learning Genetic Programming Combiner," Sensors, vol. 23, no. 7, Apr. 2023, Art. no. 3736. DOI: https://doi.org/10.3390/s23073736
K.-T. Nguyen, Q.-T. Ha, and X.-H. Phan, "Dynamic Windowing Strategies for Concept Drift Type Classification in Data Streams," in 2024 IEEE International Conference on Progress in Informatics and Computing, Shanghai, China, 2024, pp. 70–74. DOI: https://doi.org/10.1109/PIC62406.2024.10892652
G. J. Aguiar and A. Cano, "A comprehensive analysis of concept drift locality in data streams," Knowledge-Based Systems, vol. 289, Apr. 2024, Art. no. 111535. DOI: https://doi.org/10.1016/j.knosys.2024.111535
A. L. Suárez-Cetrulo, D. Quintana, and A. Cervantes, "A survey on machine learning for recurring concept drifting data streams," Expert Systems with Applications, vol. 213, Mar. 2023, Art. no. 118934. DOI: https://doi.org/10.1016/j.eswa.2022.118934
K. Goel and S. Batra, "Adaptive online learning for classification under concept drift," International Journal of Computational Science and Engineering, vol. 24, no. 2, pp. 128–135, Jan. 2021. DOI: https://doi.org/10.1504/IJCSE.2021.115099
P. S and A. U. R, "Ensemble framework for concept drift detection and class imbalance in data streams," Multimedia Tools and Applications, vol. 84, no. 11, pp. 8823–8837, Mar. 2025.
J. Montiel, R. Mitchell, E. Frank, B. Pfahringer, T. Abdessalem, and A. Bifet, "Adaptive XGBoost for Evolving Data Streams," in 2020 International Joint Conference on Neural Networks, Glasgow, UK, 2020, pp. 1–8. DOI: https://doi.org/10.1109/IJCNN48605.2020.9207555
A. M. Paim and F. Enembreck, "Adaptive random tree ensemble for evolving data stream classification," Knowledge-Based Systems, vol. 309, Jan. 2025, Art. no. 112830. DOI: https://doi.org/10.1016/j.knosys.2024.112830
H. K. Fatlawi and A. Kiss, "Efficiency improvement of adaptive random forest using principal component analysis for mining data stream," Annales Universitatis Scientiarum Budapestinensis de Rolando Eötvös Nominatae. Sectio computatorica, vol. 55, pp. 39–48, Jan. 2023. DOI: https://doi.org/10.71352/ac.55.039
Ł. Korycki and B. Krawczyk, "Class-Incremental Experience Replay for Continual Learning under Concept Drift," in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Nashville, TN, USA, 2021, pp. 3644–3653. DOI: https://doi.org/10.1109/CVPRW53098.2021.00404
Y. Wu, L. Liu, Y. Yu, G. Chen, and J. Hu, "Online Adaptive Ensemble Enhanced Anomaly Detection for Addressing Concept Drift in IoT Systems." TechRxiv, Jan. 02, 2024. DOI: https://doi.org/10.36227/techrxiv.23304461.v2
K. A. M. Junaid, D. Paulraj, and T. Sethukarasi, "A comprehensive ensemble classification techniques detecting and managing concept drift in dynamic imbalanced data streams," Wireless Networks, vol. 31, no. 1, pp. 19–30, Jan. 2025. DOI: https://doi.org/10.1007/s11276-024-03742-0
S. Arora, R. Rani, and N. Saxena, "A systematic review on detection and adaptation of concept drift in streaming data using machine learning techniques," WIREs Data Mining and Knowledge Discovery, vol. 14, no. 4, July 2024, Art. no. e1536. DOI: https://doi.org/10.1002/widm.1536
A. Cano and B. Krawczyk, "ROSE: robust online self-adjusting ensemble for continual learning on imbalanced drifting data streams," Machine Learning, vol. 111, no. 7, pp. 2561–2599, July 2022. DOI: https://doi.org/10.1007/s10994-022-06168-x
Downloads
How to Cite
License
Copyright (c) 2026 Sudianto Sudianto, Aminatus Sa'adah, Brian Farrel Arkana
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License 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) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
