Skip to content
Review Open access

Explainable Aspect-Based Sentiment Analysis for Marine Tourism Using Large-Scale Language Models

2026 · International Journal of Advanced Computer Science and Applications · 0 citations · 28 references

Abstract

Marine tourism is a strategic sector heavily influenced by tourists' perceptions and experiences, which are captured in user-generated content across various digital platforms. However, the multifaceted, informal, and ambiguous nature of reviews poses challenges for sentiment analysis based on conventional methods. This study proposes an aspect-based sentiment analysis (ABSA) framework using a Large Language Model (LLM) integrated with Explainable Artificial Intelligence (XAI) to analyze cross-platform marine tourism reviews. The proposed approach includes text reflection preprocessing, aspect extraction, sentiment classification based on zero-shot and few-shot learning schemes, and XAI integration to improve the interpretability of the results through the contribution of keywords and evidence phrases. Model evaluation is conducted by comparing the model output against reference annotations on a subset of review data using precision, recall, and F1-score metrics at the aspect level. Experimental results show that the zero-shot scheme produces moderate performance with an accuracy and macro-average F1 score of 0.33, while the application of some-shot learning significantly improves performance with an accuracy of 0.87 and a macro-average F1 score of 0.87. The integration of XAI shows that the resulting sentiment prediction model is supported by relevant linguistic evidence, thereby increasing transparency and trust in the analysis results. These findings confirm that the proposed ABSA-based LLM framework is effective, interpretative, and has the potential to be used as a decision-support tool in the management and development of data-driven marine tourism destinations.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.