AN EXPLORATION OF INTERACTIONS BETWEEN URBAN HERITAGES AND TOURIST’S DIGITAL FOOTPRINT: NETWORK AND TEXTUAL ANALYSIS VIA GEOTAGGED FLICKR DATA IN AMSTERDAM

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume X-4/W3-2022 7th International Conference on Smart Data and Smart Cities (SDSC), 19–21 October 2022, Sydney, Australia AN EXPLORATION OF INTERACTIONS BETWEEN URBAN HERITAGES AND TOURIST’S DIGITAL FOOTPRINT: NETWORK AND TEXTUAL ANALYSIS VIA GEOTAGGED FLICKR DATA IN AMSTERDAM S. S. Karayazi1, * , G. Dane¹, T. Arentze¹ ¹Urban Systems and Real Estate, Department of Built Environment, Eindhoven University of Technology, The Netherlands (s.s.karayazi, g.z.dane, t.a.arentze)@tue.nl Commission IV, WG IV/9 KEY WORDS: LBSN data, Flickr, Network mining, Text mining, Heatmap, Amsterdam, Urban heritage, Tourism ABSTRACT: Spatial information retrieved by geotagged social media data allows the analysis of when and where questions and supports a better understanding of people’s spatial interaction. The purpose of this paper is to reveal alternative heritage spots for reducing tourism pressure in certain areas within Amsterdam’s historical core by presenting tourists’ points of interests (POIs), their patterns between POIs, and the sentiments attached to these POIs. To fulfil the research aim, network analysis, textual analysis, and heat maps were conducted with geotagged Flickr data representing tourists’ uploaded images. The results show that the Flickr data set was useful to reveal the existing POIs and their relations. Moreover, the further analysis that is based on the intersection between the revealed spatial patterns and Amsterdam heritage sites showed alternative POIs nearby current POIs. Based on the results, we demonstrated how a dataset constructed from geotagged Flickr data can provide useful practical information for sustainable tourism development. Our research has the potential to support urban heritage and tourism researchers and policy makers with a better understanding of POIs, their relations and possible other POIs. The outcomes of this research can advise heritage tourists on alternative POIs to visit, and policy makers to plan alternative POIs. 1. INTRODUCTION Over the last years, increasing tourism activities and the amount of tourists in European cities such as Amsterdam, Barcelona, Venice, Berlin, Copenhagen, have been detrimental to heritage artifacts and their values that are considered as magnets for tourists (Hospers, 2019). According to The World Tourism Organization (UNWTO, 2018), overtourism is described as “the overcrowding from an excess of tourists and its impact on a destination, or parts thereof, that excessively influences perceived quality of life of citizens and/or quality of tourist experiences in a negative way.” In that sense, destinations that are attractive to tourists are affected by the consequences of mass tourism activities. Therefore, an increasing need emerges to understand and monitor tourist patterns by considering their relation with the environment in space and time in order to combat the challenges of overtourism. In historic cities, certain heritage buildings and areas become very attractive to tourists because of their significance, overpromotion, and popularity (García-Hernández et al., 2017), while some heritage areas may not attract tourists and become underrepresented. There is a need to understand tourists’ movements in the city, and how tourists perceive and experience different places (Trinh & Ryan, 2017). Based on this understanding, tourists can be provided with location suggestions not only of well-known places but also underrepresented areas with similar heritage types for reducing tourism pressure by distributing tourists throughout the city. That can lead to developing sustainable tourism policies in overly touristic heritage cities. With the emergence of big data from newly available sources, such as location-based social networks (LBSN), volunteered geographic information (VGI), such as Flickr, Foursquare, which provide a wide range of spatial and non-spatial information, it is possible to conduct evidence-based urban studies research (Song & Liu, 2017). The dimensions of urban tourism and heritage studies that utilized LBSN data sources differ. For instance, van der Zee et al. (2018), focused on destination management by utilizing the TripAdvisor dataset to reveal tourist’s digital footprint from five Flemish historical cities. They found that spatial clustering and hotspot analysis are capable of showing tourists’ patterns and providing new knowledge about actual use of space by users and its online representation. Karayazi et al. (2021), utilized the combination of multisource information such as heritage data, supporting products data (i.e., attractions, museum, open market, shopping) and Flickr data to understand attractive heritage locations and the built environment characteristics that make them attractive. They conducted cluster analysis with density-based spatial clustering of applications with noise (DBSCAN) to identify POIs, then employed ordinary least square and geographically weighted regression, and revealed that tourist’s POIs were concentrated within Amsterdam’s historical core whereas locals were distributed over the city. In addition, they emphasized that the combination of less attractive heritage with strong influential supporting products (i.e., tram-metro stations) could introduce to sustainable tourism by promoting less attractive heritages transforming into attractive in Amsterdam. Ginzarly et al. (2018), conducted an analysis of Flickr photos and the analysis of their tags for mapping historic urban landscape. First, they classified photographs as tangible and intangible images to understand what the scenes depict. Second, they focused on textual analysis of Flickr tags with quantitative and categorical analysis. They found that the tags could explain the spatial perception of users. These studies concluded that LBSN data is qualified to capture the relations between visitors’ movements and perceptions. Regarding the methodology to utilize newly available data such as Global Positioning System (GPS) and LBSN, in tourism literature, * Corresponding author This contribution has been peer-reviewed. The double-blind peer-review was conducted on the basis of the full paper. https://doi.org/10.5194/isprs-annals-X-4-W3-2022-105-2022 | © Author(s) 2022. CC BY 4.0 License. 105 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume X-4/W3-2022 7th International Conference on Smart Data and Smart Cities (SDSC), 19–21 October 2022, Sydney, Australia several clustering algorithms and network analysis have been frequently applied for understanding tourist movements and patterns. Dane et al. (2020), focused on visitor flows utilizing GPS data to detect the area of interest locations. They analysed visitors’ temporal and spatial behaviour including origindestination and intra-event destinations by means of network analysis. Grinberger et al. (2014), identified a grou (...truncated)