Ensemble Learning for Multi-Source Multi-Domain Sentiment Analysis

Sentiment analysis systems are typically trained and evaluated on a single data source and domain, limiting their reliability when applied across sources that differ in vocabulary, review length, and writing style. This paper presents an ensemble learning framework for multi-source, multi-domain sentiment classification evaluated across three structurally distinct sources: Twitter (short, informal), TripAdvisor (long, first-person), and Rotten Tomatoes (short, editorial). A unified pipeline combining text normalization with a TF-IDF-weighted Word2Vec (Skip-gram, 200-dim) representation was used to train six base classifiers (Naive Bayes, KNN, Logistic Regression, SVM, Decision Tree, MLP) and four ensembles (Bagging, Boosting, Stacking, Voting) under an identical 5-fold cross-validation protocol. On a held-out, domain-stratified test set of 2,360 samples, SVM achieved the best overall performance (83.05% accuracy, 82.28% F1), narrowly outperforming Stacking (82.58%) and Voting (81.78%). A domain-wise breakdown revealed that TripAdvisor (88.13% F1) was classified far more reliably than Rotten Tomatoes (78.41%) or Twitter (76.27%), a gap associated with review length rather than dataset size. These findings show that ensembling does not guarantee improvement over an already-strong individual classifier, and that domain-aware evaluation is essential in multi-source sentiment analysis.

Sentiment Analysis; Ensemble Learning; Multi-Domain Classification; Multi-Source Text Mining; Word2Vec; TF-IDF Weighting; Text Classification

1. J. Kazmaier and J. H. van Vuuren, "The power of ensemble learning in sentiment analysis," Expert Syst. Appl., vol. 187, p. 115819, 2022. https://doi.org/10.1016/j.eswa.2021.115819 [Google Scholar] [Crossref]

2. R. Kora and A. Mohammed, "An enhanced approach for sentiment analysis based on meta-ensemble deep learning," Soc. Netw. Anal. Min., vol. 13, p. 38, 2023. https://doi.org/10.1007/s13278-023-01043-6 [Google Scholar] [Crossref]

3. S. Shah, H. Ghomeshi, E. Vakaj, E. Cooper, and R. Mohammad, "An ensemble-learning-based technique for bimodal sentiment analysis," Big Data Cogn. Comput., vol. 7, no. 2, p. 85, 2023. https://doi.org/10.3390/bdcc7020085 [Google Scholar] [Crossref]

4. M. Ghosh, A. Chakraborty, and I. Pal, "An ensemble approach to enhance the efficacy of sentiment prediction," Int. J. Comput. Theory Eng., vol. 16, no. 2, pp. 55-65, 2024. https://doi.org/10.7763/ijcte.2024.v16.1354 [Google Scholar] [Crossref]

5. Y. Kong, Z. Xu, and M. Mei, "Cross-domain sentiment analysis based on feature projection and multi-source attention in IoT," Sensors, vol. 23, no. 16, p. 7282, 2023. https://doi.org/10.3390/s23167282 [Google Scholar] [Crossref]

6. "Enhancing cross-domain sentiment classification through multi-source collaborative training and selective ensemble methods," J. Supercomput., 2024. https://doi.org/10.1007/s11227-024-06391-4 [Google Scholar] [Crossref]

7. "Cross-domain sentiment classification via deep reinforcement learning," in Proc. MLNLP '22, 2022. https://doi.org/10.1145/3578741.3578807 [Google Scholar] [Crossref]

8. "Enhancing multi-source cross-domain sentiment classification with generative adversarial networks and transfer learning," Cluster Comput., 2025. https://doi.org/10.1007/s10586-025-05653-x [Google Scholar] [Crossref]

9. M. M. Rahman and M. N. Islam, "Exploring the performance of ensemble machine learning classifiers for sentiment analysis of COVID-19 tweets," in Sentimental Analysis and Deep Learning, AISC vol. 1408, Singapore: Springer, 2022. https://doi.org/10.1007/978-981-16-5157-1_30 [Google Scholar] [Crossref]

10. M. S. Kalaivani, S. Jayalakshmi, and R. Priya, "Comparative analysis of sentiment classification using machine learning techniques on Twitter data," Int. J. Health Sci., vol. 6, no. S2, pp. 8273-8280, 2022. https://doi.org/10.53730/ijhs.v6nS2.7098 [Google Scholar] [Crossref]

11. S. Anis, S. Saad, and M. Aref, "Sentiment analysis of hotel reviews using machine learning techniques," in Proc. AISI 2020, AISC vol. 1261, Cham: Springer, 2021. https://doi.org/10.1007/978-3-030-58669-0_21 [Google Scholar] [Crossref]

12. K. Puh and M. Bagić Babac, "Predicting sentiment and rating of tourist reviews using machine learning," J. Hosp. Tour. Insights, vol. 6, no. 3, pp. 1188-1204, 2023. https://doi.org/10.1108/JHTI-02-2022-0078 [Google Scholar] [Crossref]

13. M. A. Kausar, S. O. Fageeri, and A. Soosaimanickam, "Sentiment classification based on machine learning approaches in Amazon product reviews," Eng. Technol. Appl. Sci. Res., vol. 13, no. 3, pp. 10849-10855, 2023. https://doi.org/10.48084/etasr.5854 [Google Scholar] [Crossref]

14. M. F. bin Harunasir, N. Palanichamy, S.-C. Haw, and K.-W. Ng, "Sentiment analysis of Amazon product reviews by supervised machine learning models," J. Adv. Inf. Technol., vol. 14, no. 4, pp. 857-862, 2023. https://doi.org/10.12720/jait.14.4.857-862 [Google Scholar] [Crossref]

15. "Analyzing Amazon products sentiment: A comparative study of machine and deep learning, and transformer-based techniques," Electronics, vol. 13, no. 7, p. 1305, 2024. https://doi.org/10.3390/electronics13071305 [Google Scholar] [Crossref]

16. M. S. Başarslan and F. Kayaalp, "Sentiment analysis with ensemble and machine learning methods in multi-domain datasets," Turkish J. Eng., vol. 7, no. 2, pp. 141-148, 2023. https://doi.org/10.31127/tuje.1079698 [Google Scholar] [Crossref]

17. M. S. Başarslan and F. Kayaalp, "Sentiment analysis using a deep ensemble learning model," Multimed. Tools Appl., vol. 83, pp. 42207-42231, 2024. https://doi.org/10.1007/s11042-023-17278-6 [Google Scholar] [Crossref]

18. M. R. Nugraha, M. D. Purbolaksono, and W. Astuti, "Sentiment analysis on movie review from Rotten Tomatoes using modified balanced random forest method and Word2Vec," Building Informat. Technol. Sci. (BITS), vol. 5, no. 1, pp. 153-161, 2023. https://doi.org/10.47065/bits.v5i1.3596 [Google Scholar] [Crossref]

19. D. Nath and J. Roy, "Forecast of movie sentiment based on multi label text classification on Rotten Tomatoes using multiple machine and deep learning technique," in Proc. ICCCSP 2023, IFIP AICT vol. 670, Cham: Springer, 2023. https://doi.org/10.1007/978-3-031-39811-7_11 [Google Scholar] [Crossref]

20. D. D. Tran, T. T. Nguyen, and T. Dao, "Sentiment analysis of movie reviews using machine learning techniques," in Proc. 6th Int. Congr. Inf. Commun. Technol., LNNS vol. 235, Singapore: Springer, 2022. https://doi.org/10.1007/978-981-16-2377-6_34 [Google Scholar] [Crossref]

21. "Sentimental analysis of movie reviews using machine learning," ITM Web Conf., vol. 53, p. 02006, 2023. https://doi.org/10.1051/itmconf/20235302006 [Google Scholar] [Crossref]

22. "A two-stage voting-boosting ensemble learning in social network sentiment classification," Entropy, vol. 25, no. 4, p. 555, 2023. https://doi.org/10.3390/e25040555 [Google Scholar] [Crossref]

23. "A stacking ensemble based on lexicon and machine learning methods for the sentiment analysis of tweets," Mathematics, vol. 12, no. 21, p. 3405, 2024. https://doi.org/10.3390/math12213405 [Google Scholar] [Crossref]

24. V. Kp, R. Ab, G. Hl, V. Ravi, and M. Krichen, "A tweet sentiment classification approach using an ensemble classifier," Int. J. Cogn. Comput. Eng., vol. 5, pp. 170-177, 2024. https://doi.org/10.1016/j.ijcce.2024.04.001 [Google Scholar] [Crossref]

25. "A hybrid stacked ensemble learning framework for multilabel text emotion detection," Sci. Rep., 2026. https://doi.org/10.1038/s41598-026-38172-9 [Google Scholar] [Crossref]

26. "Effectiveness of Word2Vec and TF-IDF in sentiment classification on online investment platforms using support vector machine," JIPI, vol. 10, no. 2, 2025. https://doi.org/10.29100/jipi.v10i2.6055 [Google Scholar] [Crossref]

27. "Comparative analysis of TF-IDF and Word2Vec in sentiment analysis: A case of food reviews," ITM Web Conf., vol. 70, p. 02013, 2025. https://doi.org/10.1051/itmconf/20257002013 [Google Scholar] [Crossref]

28. "Text classification algorithm of tourist attractions subcategories with modified TF-IDF and Word2Vec," PLOS ONE, 2024. https://doi.org/10.1371/journal.pone.0305095 [Google Scholar] [Crossref]

29. J. C. Gope, T. Tabassum, M. M. Mabrur, K. Yu, and M. Arifuzzaman, "Sentiment analysis of Amazon product reviews using machine learning and deep learning models," in Proc. 2022 ICAEEE, 2022. https://doi.org/10.1109/ICAEEE54957.2022.9836420 [Google Scholar] [Crossref]

30. N. Sultan, "Sentiment analysis of Amazon product reviews using supervised machine learning techniques," Knowl. Eng. Data Sci., vol. 5, no. 1, pp. 101-108, 2022. https://doi.org/10.17977/UM018V5I12022P101-108 [Google Scholar] [Crossref]

31. R. S. Monsoor, T. S. Tamanna, S. Khan, S. Hoque, M. Islam, E. R. Rhythm, M. H. K. Mehedi, and A. A. Rasel, "Sentiment analysis of Amazon reviews using machine learning classifier," in Proc. 2023 26th ICCIT, 2023. https://doi.org/10.1109/ICCIT60459.2023.10441259 [Google Scholar] [Crossref]

32. G. Manias, A. Mavrogiorgou, A. Kiourtis, C. Symvoulidis, and D. Kyriazis, "Multilingual text categorization and sentiment analysis: A comparative analysis of the utilization of multilingual approaches for classifying Twitter data," Neural Comput. Appl., 2023. https://doi.org/10.1007/s00521-023-08629-3 [Google Scholar] [Crossref]

33. "Fine-tuning XLNet for Amazon review sentiment analysis: A comparative evaluation of transformer models," ETRI J., 2026. https://doi.org/10.4218/etrij.2024-0318 [Google Scholar] [Crossref]

34. U. D. Prasan, M. Ruchita, T. Dinesh, S. Manohar, S. Prasanth, and Saurab, "Sentiment analysis of Amazon product reviews using machine learning algorithms," Int. J. Eng. Res. Appl., vol. 13, no. 4, pp. 60-64, 2023. https://doi.org/10.9790/9622-13046064 [Google Scholar] [Crossref]

35. G. Roccabruna, S. Azzolin, and G. Riccardi, "Multi-source multi-domain sentiment analysis with BERT-based models," in Proc. 13th Conf. Lang. Resour. Eval. (LREC 2022), Marseille, France, 2022, pp. 581-589. https://aclanthology.org/2022.lrec-1.62/ [Google Scholar] [Crossref]

• Assessment of the Role of Artificial Intelligence in Repositioning TVET for Economic Development in Nigeria
• Teachers’ Use of Assure Model Instructional Design on Learners’ Problem Solving Efficacy in Secondary Schools in Bungoma County, Kenya
• “E-Booksan Ang Kaalaman”: Development, Validation, and Utilization of Electronic Book in Academic Performance of Grade 9 Students in Social Studies
• Analyzing EFL University Students’ Academic Speaking Skills Through Self-Recorded Video Presentation
• Major Findings of The Study on Total Quality Management in Teachers’ Education Institutions (TEIs) In Assam – An Evaluative Study