arXiv subjects

Thi-Phuong Le

Publications and source records attributed to Thi-Phuong Le.

3 recordsLinked to original sources

arXiv2026

XAI-enhanced Comparative Opinion Mining via Aspect-based Scoring and Semantic Reasoning

Comparative opinion mining involves comparing products from different reviews. However, transformer-based models designed for this task often lack transparency, which can adversely hinder the development of trust in users. In this paper, we propose XCom, an enhanced transformer-based model separated into two principal modules, i.e., (i) aspect-based rating prediction and (ii) semantic analysis for comparative opinion mining. XCom also incorporates a Shapley additive explanations module to provide interpretable insights into the model's deliberative decisions. Empirically, XCom achieves leading performances compared to other baselines, which demonstrates its effectiveness in providing meaningful explanations, making it a more reliable tool for comparative opinion mining. Source code is available at: https://anonymous.4open.science/r/XCom.

cs.CL↗

arXiv2026

Comparing Without Saying: A Dataset and Benchmark for Implicit Comparative Opinion Mining from Same-User Reviews

Existing studies on comparative opinion mining have mainly focused on explicit comparative expressions, which are uncommon in real-world reviews. This leaves implicit comparisons - here users express preferences across separate reviews - largely underexplored. We introduce SUDO, a novel dataset for implicit comparative opinion mining from same-user reviews, allowing reliable inference of user preferences even without explicit comparative cues. SUDO comprises 4,150 annotated review pairs (15,191 sentences) with a bi-level structure capturing aspect-level mentions and review-level preferences. We benchmark this task using two baseline architectures: traditional machine learning- and language model-based baselines. Experimental results show that while the latter outperforms the former, overall performance remains moderate, revealing the inherent difficulty of the task and establishing SUDO as a challenging and valuable benchmark for future research.

cs.CL↗

arXiv2025

Deep Learning for Automated Identification of Vietnamese Timber Species: A Tool for Ecological Monitoring and Conservation

Accurate identification of wood species plays a critical role in ecological monitoring, biodiversity conservation, and sustainable forest management. Traditional classification approaches relying on macroscopic and microscopic inspection are labor-intensive and require expert knowledge. In this study, we explore the application of deep learning to automate the classification of ten wood species commonly found in Vietnam. A custom image dataset was constructed from field-collected wood samples, and five state-of-the-art convolutional neural network architectures--ResNet50, EfficientNet, MobileViT, MobileNetV3, and ShuffleNetV2--were evaluated. Among these, ShuffleNetV2 achieved the best balance between classification performance and computational efficiency, with an average accuracy of 99.29\% and F1-score of 99.35\% over 20 independent runs. These results demonstrate the potential of lightweight deep learning models for real-time, high-accuracy species identification in resource-constrained environments. Our work contributes to the growing field of ecological informatics by providing scalable, image-based solutions for automated wood classification and forest biodiversity assessment.

cs.CV↗