Imran, MuhammadRasheed, TayyabGómez-Rodríguez, Carlos2026-05-292026-05-292025M. Imran, T. Rasheed, and C. Gómez-Rodríguez, "Enhancing Transformer-Based Sentiment Analysis for the Rest-Mex 2025 Challenge: A Hybrid Strategy with Oversampling, Back-Translation, and Transformers," in Workshop Researching on Evaluating Sentiment and Textual Instances Selection for Mexican Magical Towns (REST-MEX 2025) co-located with IberLEF 2025, CEUR Workshop proceedings, vol. 4098, 2025.1613-0073https://hdl.handle.net/2183/48415Presented at: Researching on Evaluating Sentiment and Textual Instances Selection for Mexican Magical Towns (REST-MEX 2025), at IberLEF 2025: Natural Language Processing Challenges for Spanish and other Iberian Languages, September 2025, Zaragoza, Spain The code is available in the following GitHub repository. https://github.com/chimran135/Sentiment-Analysis-Rest-Mex-2025[Abstract]: This paper presents a sentiment analysis framework for the Rest-Mex 2025 challenge, focused on Spanish-language reviews of Mexican Magical Towns. The task involves predicting sentiment polarity (1-5), classifying attraction type (Hotel, Restaurant, Attraction), and identifying the correct town from a list of 60. To address class imbalance, we propose a hybrid augmentation approach combining oversampling and back-translation using both structurally similar and dissimilar languages. Two transformer-based models roberta-base-bne and twitter-xlm-roberta-base are fine-tuned on the augmented datasets. The hybrid strategy, particularly with the multilingual model, achieved the best results, demonstrating improved performance and generalization across all subtasks. Our system achieved 4th place in the overall sentiment analysis track of the Rest-Mex 2025 shared task competing against 35 participating teams which demonstrates the robustness of our approach in sentiment classification across multiple subtasks. © 2025 Copyright for this paper by its authors.engAttribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/Back-translationNLPOversamplingSentiment AnalysisTransformersTripAdvisor reviewsconference outputopen access