Scholarlink

This study analyzes the integration of Artificial Intelligence and Big Data Sentiment Analysis to support sustainable tourism development in the Puncak area, West Java. Data was obtained from approximately 10,000 online tourist reviews (Google Reviews, TripAdvisor, Twitter) and analyzed using Naive Bayes algorithms, Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and Latent Dirichlet Allocation (LDA) for topic mapping. The results showed that the majority of tourists gave positive sentiments (68%) regarding natural panoramas and local culinary, while traffic jams (28%) and garbage/environment (20%) were the main complaints. These findings were confirmed through interviews with stakeholders (local governments, businesses, and local communities), which confirmed the consistency between digital data and field conditions. The integration of quantitative and qualitative results resulted in policy recommendations: the application of AI for traffic management, IoT for waste management, digitalization of MSME culinary, and the development of a Smart Tourism Dashboard. The results of this study also confirm that sentiment analysis can serve as an indicator of social carrying capacity, strengthening the literature on smart sustainable tourism and supporting the UNESCO agenda and SDGs 8, 11, and 12.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integration of Artificial Intellegence and Big Data Sentimental Analysis for Sustainable Tourism Development in the Puncak Area, West Java

  • 章节

  • 发表日期：

    2026年

查看全文
  • Ardiyanto Maksimilianus Gai,
  • Nurul Mardhiah Sitio,
  • Hadi Mulyana,
  • Syahrianti Syam,
  • Vitri Aprilla Handayani

摘要

This study analyzes the integration of Artificial Intelligence and Big Data Sentiment Analysis to support sustainable tourism development in the Puncak area, West Java. Data was obtained from approximately 10,000 online tourist reviews (Google Reviews, TripAdvisor, Twitter) and analyzed using Naive Bayes algorithms, Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and Latent Dirichlet Allocation (LDA) for topic mapping. The results showed that the majority of tourists gave positive sentiments (68%) regarding natural panoramas and local culinary, while traffic jams (28%) and garbage/environment (20%) were the main complaints. These findings were confirmed through interviews with stakeholders (local governments, businesses, and local communities), which confirmed the consistency between digital data and field conditions. The integration of quantitative and qualitative results resulted in policy recommendations: the application of AI for traffic management, IoT for waste management, digitalization of MSME culinary, and the development of a Smart Tourism Dashboard. The results of this study also confirm that sentiment analysis can serve as an indicator of social carrying capacity, strengthening the literature on smart sustainable tourism and supporting the UNESCO agenda and SDGs 8, 11, and 12.