Abstract—Every day millions of people express their opinions, suggestions and views about accommodation, services, and tourist destinations on the web and online applications. The Google Map website was used to collect a datasets of reviews of tourist destinations in West Sumatra, Indonesia. The aim of this research is to analyze text reviews of tourist destinations so that it is known that Intent Sentiment Analysis (ISA) uses the Deep Learning Recurrent Neural Network (RNN) Long Short-Term Memory (LSTM) variant classification method with support for FastText Embedding feature extraction. The performance of the text classification model was evaluated using split data ratios of 70:30, 80:20, and 90:10. The highest accuracy rate of 97% was achieved with a data split ratio of 90:10. The four models developed succeeded in predicting the intent of sentiment analysis consisting of complaints, suggestions, opinions, statements, and appreciation. This research provides knowledge about what motivates people to write reviews on tourist destinations. This can be used as a reference source by tourist destination management in making destination management policies.
 
Keywords—Recurrent Neural Network (RNN)-Long Short-Term Memory (LSTM), FastText, Natural Language Processing (NLP), intent sentiment, tourism destination


Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.