Labuan Bajo as super-priority destinations experience improvement visit in a number of year lastly, however quality service Not yet fully fulfil expectation tourists . Study This analyze perception traveler through Aspect-Based Sentiment Analysis (ABSA) approach using the IndoBERT model. A total of 2,564 reviews multilingual from Google Maps and TripAdvisor processed through translation, pre-processing, extraction aspects, sentiment labels automatic, and model training. Four aspects analyzed based on framework SERVQUAL theory and Tourism Destination Quality: attractions, amenities, accessibility, and price. Model evaluation was conducted using precision, recall, and F1-score per aspect. The results show performance best The amenity and attraction aspects obtained the highest and most consistent scores across all metrics (around 0.83–0.88), indicating that reviews for these two aspects were more explicit and easily mapped by the model. In contrast, the access and price aspects showed lower scores (around 0.65–0.72), indicating linguistic challenges such as implicit aspects, variations in the context of the travel experience, and figurative complaints . The study This give recommendation policy connected data based direct with model findings. Limitations such as translation noise, biased datasets dominated by review positive-neutral, and not existence baseline comparison also discussed. These results confirm that ABSA approach can help stakeholder’s policy, however Still need improvement through other models such as IndoBERTweet, mBERT, or IndoBART.
Copyrights © 2026