Scoping out urban areas of tourist interest though geolocated social media data: Bucharest as a case study

Abstract

Social media data has frequently sourced research on topics such as traveller planning or the factors that influence travel decisions. The literature on the location of tourist activities, however, is scarce. The studies in this line that do exist focus mainly on identifying points of interest and rarely on the urban areas that attract tourists. Specifically, as acknowledged in the literature, tourist attractions produce major imbalances with respect to adjacent urban areas. The present study aims to fill this research gap by addressing a twofold objective. The first was to design a methodology allowing to identify the preferred tourist areas based on concentrations of places and activities. The tourist area was delimited using Instasights heatmaps information and the areas of interest were identified by linking data from the location-based social network Foursquare to TripAdvisor’s database. The second objective was to delimit areas of interest based on users’ existing urban dynamics. The method provides a thorough understanding of functional diversity and the location of a city’s different functions. In this way, it contributes to a better understanding of the spatial distribution imbalances of tourist activities. Tourist areas of interest were revealed via the identification of users’ preferences and experiences. A novel methodology was thus created that can be used in the design of future tourism strategies or, indeed, in urban planning. The city of Bucharest, Romania, was taken as a case study to develop this exploratory research.

رصد البصمة الرقمية السياحية ومراكز الأنشطة السياحية من خلال بيانات التوسيم الجغرافي والبيانات المحددة للموقع: مدينة الإسكندرية كدراسة حالة

“…Accordingly, tourism activity centers including shopping, eating, and nightlife are recognized by tourists' digital footprints (Mor & Dalyot, 2020;Yu et al, 2023). In this regard, identifying tourist hotspots or area of interest is critical from the perspectives of urban planning and tourism management in order to ensure accurate design of land-use and tourism-related urban policies (Martí Ciriquián et al, 2019;Nolasco-Cirugeda et al, 2022). In this field, location Based Social Networks ( LBSNs) have been extensively utilized as crucial big data sources for urban analysis (Martí et al, 2021), to providing a method for evaluating the activity pulse of the city (Martí Ciriquián et al, 2019), human mobility (Li et al, 2018), human behavior (Lee et al, 2013), urban planning, urban design, and decisionmaking processes (Padrón-Ávila & Hernández-Martín, 2017;Üsküplü et al, 2020).…”

“…These studies range from the segmentation of tourist markets using user-generated content (UGC) to exploring the behaviors within online tourist communities. Scholars such as Li et al (2018), Yubero et al (2021), andNolasco-Cirugeda et al (2022) have delved into this phenomenon. Social media platforms have effectively engaged tourists, offering them a space to exchange insights and information concerning their travel experiences as well as finding sophisticated method to illustrate individuals' spatiotemporal preferences and mobility patterns (Yu et al, 2023).…”

“…These data facilitate the visualization of segmented variables and the identification of Points of Interest (POIs) or Areas of Interest (AOIs) within urban centers (García-Palomares et al 2015;Li et al 2018). Furthermore, the analysis of LBSN data, supported by dynamic georeferenced User-Generated Content (UGC) and metadata, proves beneficial for investigating disparities and imbalances such as those arising from over tourism (Nolasco-Cirugeda et al, 2022;Encalada-Abarca, et al, 2024) or the uneven distribution of tourist flows towards specific tourist areas, leading to issues like visitor overcrowding in specific tourist zones (Jiansheng &Yanling, 2021). This phenomenon elucidates the issue of overcrowding or clustering of visitors, including tourists and local inhabitants (Jiansheng & Yanling, 2021), in areas with particular tourist attractions while neglecting other dispersed urban tourist spots offering diverse activities and amenities.…”

“…The novelty of this study is apparent in several key aspects: firstly, it concentrates on the intersections of eating, shopping, sightseeing, and nightlife activities in a chosen city for the case study (Martí et al, 2021); secondly, it presents a novel method for describing and characterizing urban tourist activity centers and identifying Areas of Interest (AOIs) from the perspective of users, utilizing Location-Based Social Networking (LBSN) data (Encalada-Abarca, et al, 2024). Consequently, it becomes possible to recognize the venues preferred by tourists, enabling the verification of urban areas that attract tourists' attention and providing guidance for the city's development based on patterns of user activity (Nolasco-Cirugeda et al, 2022). Thirdly, the proposed reference framework incorporates LBSN data, serving as a supplementary tool for urban planning and decision-making processes aimed at improving city urban dynamics (Gao et al, 2024) and to achieve organized tourism development of cities supporting the wellbeing of current and future tourists flow (Sedarati, 2019).…”

“…Moreover, this work offers a scientific foundation for enhancing and managing tourism spaces, traffic, and service facilities in specific regions (Gu et al, 2023). This approach can also contribute to orientating urban land-use planning (Mou, 2022) and formulating tourism strategies that align with urban revitalization and regeneration (Yubero et al, 2021) to address imbalances in various areas, thus mitigating issues like over-tourism (Nolasco-Cirugeda et al, 2022), gentrification, and uneven distribution of tourist flow towards specific destinations.…”