Scholarlink

<p>The advancement of mobility technology enables the collection of real-time data about tourists in specific locations, capturing their geographical and temporal behavior. Movement data has become an essential alternative data source used in tourism studies. Taxis serve as a significant mode of transportation for tourists visiting new cities. However, a key challenge in utilizing taxi GPS data in the tourism domain is the lack of semantic information regarding trip purpose and user profile that could facilitate an in-depth analysis of tourist behavior. Hence, this paper proposes the TOURISTA model, a tourist trip inference method based on a rule-based and probabilistic approach. This model infers the purpose of tourist trajectories based on activities and expenditures, considering origin–destination locations. We enhance an existing probabilistic model by incorporating various data sources, including taxi trajectory data, social media data, and place data. We examine actual tourist activity from social media data to develop an activity popularity model, integrate it with trip and place information, and infer tourist trips using the probabilistic model. In our experiment, we compared the activity proportions of three baseline methods with the results obtained from the Tourism Authority of Thailand’s (TAT) tourist behavior survey. Our analysis focused on five specific activities: FoodAndDrink, Spa, Nightlife, Religious/Cultural, and Leisure. The results of our proposed method closely align with the survey data across several activity categories. We applied data analysis techniques to a case study during the Songkran Festival in Bangkok to reveal tourists’ travel characteristics, activities, movement behavior, and popular destinations. The analysis results demonstrate the utility of our study in understanding tourist flow and identifying high-density tourist locations at different times, which is crucial for planning or marketing tourism campaigns targeted at specific tourist groups. Government officials and tourism businesses can leverage this information to better plan or market their tourism campaigns.</p>

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

A Tourist Behavior Analysis Using Probabilistic-Based Tourist Trip Inference from Taxi GPS and Social Media Data

  • 期刊论文

  • 发表日期：

    2025年9月3日

查看全文
  • Pattama Krataithong,
  • Chutiporn Anutariya,
  • Marut Buranarach

摘要

The advancement of mobility technology enables the collection of real-time data about tourists in specific locations, capturing their geographical and temporal behavior. Movement data has become an essential alternative data source used in tourism studies. Taxis serve as a significant mode of transportation for tourists visiting new cities. However, a key challenge in utilizing taxi GPS data in the tourism domain is the lack of semantic information regarding trip purpose and user profile that could facilitate an in-depth analysis of tourist behavior. Hence, this paper proposes the TOURISTA model, a tourist trip inference method based on a rule-based and probabilistic approach. This model infers the purpose of tourist trajectories based on activities and expenditures, considering origin–destination locations. We enhance an existing probabilistic model by incorporating various data sources, including taxi trajectory data, social media data, and place data. We examine actual tourist activity from social media data to develop an activity popularity model, integrate it with trip and place information, and infer tourist trips using the probabilistic model. In our experiment, we compared the activity proportions of three baseline methods with the results obtained from the Tourism Authority of Thailand’s (TAT) tourist behavior survey. Our analysis focused on five specific activities: FoodAndDrink, Spa, Nightlife, Religious/Cultural, and Leisure. The results of our proposed method closely align with the survey data across several activity categories. We applied data analysis techniques to a case study during the Songkran Festival in Bangkok to reveal tourists’ travel characteristics, activities, movement behavior, and popular destinations. The analysis results demonstrate the utility of our study in understanding tourist flow and identifying high-density tourist locations at different times, which is crucial for planning or marketing tourism campaigns targeted at specific tourist groups. Government officials and tourism businesses can leverage this information to better plan or market their tourism campaigns.