Hariyono, Aji Prasetya Wibawa, Erina Fika Noviani, Giovanny Cyntia Lauretta, Hana Rachma Citra, Agung Bella Putra Utama, Felix Andika Dwiyanto
This study examines the mood of tourist evaluations for the Nusantara Temples, such as Borobudur, Prambanan, Ijo, Plaosan, and Mendut Temples, on TripAdvisor using stochastic gradient descent (SGD), logistic regression (LR), and support vector machine (SVM) classification techniques. The study examines the viewpoints and encounters of tourists from different nations on Indonesia's cultural legacy through English-language evaluations. The evaluation findings show that LR achieves the highest performance in sentiment classification, with an accuracy rate of 91.66%. The research offers valuable insights but has limits in portraying local visitors and relies heavily on the English language. Future studies might focus on doing sentiment analysis on more historical tourism sites in Indonesia, integrating multilingual data, and experimenting with novel categorization methods. This study significantly enhances our understanding of how technology and social media impact tourists' impressions of cultural heritage in the digital age via strengthening analytical methodologies and investigating alternative destinations. © Authors.
Department of History, Universitas Negeri Malang, Malang, 65145, Indonesia; Department of Electrical Engineering and Informatics, Universitas Negeri Malang, Malang, 65145, Indonesia; Faculty of Computer Science, AGH University of Krakow, Krakow, 30-059, Poland
