From Social Sensing to Tourism Sensing: A Tentative Discussion
Xiao Wenjie1,3 and Liu Yi1,2*
1School of Tourism Management, Sun Yat-sen University, Guangzhou, China
2Key Laboratory of Intelligent Assessment Technology for Sustainable Tourism, Ministry of Culture and Tourism, Zhuhai, China
3School of Tourism, Jishou University, Zhangjiajie, China
Submission: June 13, 2024;Published: July 01,2024
*Corresponding author: Liu Yi, School of Tourism Management, Sun Yat-sen University, Guangzhou, and Key Laboratory of Intelligent AssessmentTechnology for Sustainable Tourism,Ministry of Culture and Tourism, Zhuhai, China. Email: liuyi89@mail.sysu.edu.cn
How to cite this article: Xiao Wenjie and Liu Yi*. From Social Sensing to Tourism Sensing: A Tentative Discussion. Glob J Tourism Leisure & hosp manag. 2024; 1(4): 555575 DOI:10.19080/GJTLH.2024.01.555575.
Keywords: Social sensing, Tourism sensing, Tourist Destination, Points of Interests, Tourism sites
Introduction
Tourism is a multifaceted social and economic sector that involves various parties and is closely connected to different industries [1]. It is characterized by a significant level of uncertainty and constant changes. Tourism statistics and sustainability monitoring encounter obstacles due to the distinctiveness of tourists and their behaviors, the intricacy of tourism operations, and the intricate nature of the evolution of tourism destinations. Developing strategies and techniques to enhance efficient monitoring in the tourism business is a crucial and pressing new proposal.
This article will examine the pressing issues that require resolution through the use of big data monitoring. It will also evaluate the difficulties associated with implementing social sensing in the tourism industry and present a research framework for tourism sensing based on these findings. The introduction of the concept of social sensing and its research framework offers novel insights for studying tourist statistics and monitoring. It facilitates the coordination between tourism and land, and presents a viable approach to foster the growth of tourism destinations.
The Concept of Sustainomics
The term Sustainomics connect primarily to the sustainable development paradigm [1] and is defined as an integrative, balanced and practical framework aimed at improving sustainable development practices in various disciplines. First coined by Munasinghe [2] and reproduced by the Encyclopedia of the International Society of Ecological Economics (2024), Sustainomics seeks to address the complexity of sustainability dimensions through the following principles: promoting an equilibrium among social, economic and environmental factors, ensuring that all stakeholder viewpoints are considered, and emphasizing practical applications of sustainability in the real world.
Perspective on Big Data: Monitoring Tourism with Big Data
Since the inception of tourism big data research in 2013, the academic community focused on tourism has generated valuable research findings, particularly in the areas of tourists, tourism flows, and tourism destinations.
Tourists
With the assistance of the “affective computing” paradigm and the utilization of big data, the academic community in the field of tourism has created numerous models for evaluating emotions. Liu et al. [2] created a TSE model that utilized UGC text data as the data source, effectively addressing the issue of limited interpretability in the machine learning model [2]. Kang et al. [3] utilized deep learning techniques to address challenges such as cross-cultural bias in text data sources and the absence of universal models by leveraging UGC expression photos [3]. Subsequent research will investigate the spatial and temporal distribution of travelers’ emotions in tourist places, based on this foundation [4]. However, there are still existing concerns around the inherent bias of emotion, privacy security, and the inadequate timeliness of visitors’ emotions. The tourist industry has experienced a surge in the use of portable human factors devices, questionnaires, and other research methods to evaluate instant emotional experiences. This trend has been driven by the recognition of the significant value these tools provide to research situations [5].
Tourism flow
Tourism flow refers to the spatial movement of tourists in response to the closeness of tourism opportunities within a given area, regardless of its size. Tourist mobility generates tourist origin locations and tourist destinations, establishing a spatial pattern of movement between the two. There are three levels of spatial movement modes in tourism flow. The first level is the singlepoint mode, which revolves around either the tourist source or the tourist destination, with a primary focus on the destination. The second level is the point-to-point mode, which revolves around both the tourist source and the tourist destination. The third level of the tourism system is the tourist destination, which encompasses the complete tourism system [6].
Tourism flow data mostly originates from digital footprints, which encompass the textual content, images, videos, and other information that users leave on the Internet, providing insights into the locations visited by visitors. Mobile roaming data can provide a more objective measurement of tourists’ spatiotemporal behavior [7], but visual photos are more effective in explaining travel behavior [8].
Tourist Destination
The majority of research concentrate on the sensing and reputation of a certain destination. UGC data has emerged as the primary source of tourism location photographs due to its inherent advantages. Prior studies primarily utilize online texts to examine the “perceived image” and “imagery” of a place from a “emic” standpoint [9]. Recently, researchers led by Dunning have utilized deep learning algorithms to quantify the sensing of tourism sites by analyzing photos as data inputs. This approach successfully overcomes the constraints of conventional picture content analysis technologies [10].
Review
Academics commonly hold the view that big data leads to the broadening of tourism statistics and monitoring, resulting in an enhanced level of accuracy. Nevertheless, there remain several pressing issues that require immediate resolution. Existing research mostly centers around three research directions: tourist emotions, tourist destination impressions, and tourist movements. This research primarily focuses on the study of “Human,” while the investigation of “place” remains relatively limited. Nevertheless, tourism research focuses on analyzing the intricate connections between places, as well as the interplay between individuals and their surroundings [11]. Earth information science facilitates the shift in tourism research from a focus on individuals to a focus on geographical locations, thanks to the assistance of advanced technology and big data [11].
Furthermore, while considering the precision of big data, it is imperative to address consensus matters like as bias, sampling, and representativeness, as highlighted by Zheng [12]. Given the intricate and organized nature of tourism scenes, it is important to not only describe tourism phenomena based on basic spatiotemporal features, but also consider the social interactions among tourists and the interactions between tourists and the tourism environment [11]. These interactions can be observed and analyzed through geographical big data. In order to enhance the adaptability of analysis methods and incorporate factors peculiar to the tourism phenomena [13], the present analysis technology for second-order features needs to be modified.
The social sensing, a crucial scientific approach in geographic information science, introduces a research perspective known as “Human-to-place”. This perspective offers insights into the intricate dynamics of the “Human-Human” and “Human-place” relationships, while also facilitating their integration. The field of anthropology shifts its focus from the examination of individuals to the examination of geographical locations in order to offer valuable methodologies and insights.
Human and Places: Social Sensing
Social sensing is the study and technique of extracting spatiotemporal behavioral patterns from large amounts of individual data [14]. It involves analyzing how individuals interact with their surroundings and uncovering the spatiotemporal distribution, relationships, and processes of socioeconomic events. In 2015, Liu Yu implemented a comparable concept to Goodchild by replicating the notion of remote sensing. This involved the use of humans as data sensors, gathering geographical big data from numerous individuals to serve as the source of sensing data. Consequently, the sensing objects were transformed accordingly. The attributes of the natural environment were transformed into the attributes of the social economy, so introducing the notion of Social Sensing.
The First-Order Characteristics of the Place Perceived by the First-Order Attributes of Human
This study was the pioneer in deducing urban functions by analyzing the temporal distribution of taxi pick-up and drop-off sites, and accurately identifying the commercial and residential districts of the city. The research in question involves the study of movement trajectories and the simultaneous occurrence of Points of Interest (POIs). These investigations focus solely on the viewpoint of human activities and overlook the distinctive features of human activities and the constructed surroundings [15]. Therefore, Ye et al. [16] utilized Weibo social media data as a surrogate variable for activity categories, in conjunction with street view picture sensing, for the first time [16].
Previous studies infer emotions from social media content and utilize the location data provided by social media as a substitute variable for the location in order to describe the distribution of emotions in the city. Mitchell et al. [17] assessed the extent to which happiness is spread across New York and the Bay Area using Twitter data [17]. Yang et al. [18] gauged the prevalence of depressive emotions in the New York metropolitan area using Twitter Weibo [18]. Zhang et al. [19] identified six emotional characteristics, namely security, wealth, despair, and boredom, using a dataset and Tencent Street View photos [19].
Second-Order Attributes of Human and Characteristics of Place
Perceiving the attributes of locations based on the distance of spatial contact. Geospatial accessibility is determined by the spatial interaction distance between individuals in two locations. Guo et al. [20] utilized mobile phone data to derive the travel paths of older individuals who visited parks, and assessed the level of accessibility for the elderly population to these parks [20].
Assessing the attributes of a location by evaluating the intensity of spatial interactions. In a study conducted in 2015, researchers analyzed taxi trajectory data to quantify the level of spatial interaction among persons in various cities [21]. They specifically focused on Shanghai and discovered that it has a polycentric urban spatial structure. This research offers an unbiased and detailed perspective on the spatial organization of the city.
Deducing urban functions by analyzing variations in the strength of spatial interactions across time. Kang et al. [22] utilized taxi data to construct an internal spatial interaction network within the city [22]. They deduced functional zones for commuting and entertainment activities by analyzing the variations in interaction intensity across time.
Integrate the characteristics of human first-order and second-order attribute sensing
Based on the aforementioned studies, it is evident that the social function of a location is influenced not only by its own characteristics, but also by the surrounding areas. Zhu et al. [23] utilized the graph neural network model to incorporate the primary features of human visual sensing of the environment as node attributes, and the secondary attributes such as spatial interaction attributes between places as edge attributes [23]. These attributes were then integrated into a network relationship figure to infer the social function of the place.
The process of participatory evolution of perceptual space from individuals to the ground.
Zhong et al. [24] utilized bus travel data to create Singapore’s internal spatial interaction network and determine the urban spatial interaction framework [24]. By analyzing the spatial configuration over a span of three consecutive years (2010-2012), researchers were able to discern the pattern of Singapore’s multicenter city.
Review
While current social sensing research methodologies and theories offer a foundation for investigating the “human-land relationship” in tourism, they encounter the following problems when applied to this area: The social sensing framework primarily examines the attributes and development of locations, while neglecting the investigation into the connection between tourism and individuals, particularly the geographical features, structure, arrangement, and progression of the tourism sector.
Furthermore, the “Human-place-time” paradigm of social sensing primarily emphasizes a specific level of individuals, location, and timeframe, making it challenging to apply to the intricate growth of tourist attractions where time and space interact. The growth of tourist destinations involves the dynamic interplay of time and place, encompassing temporal processes and shifts in spatial linkages. Current research on social sensing mostly examines either temporal structure or spatial structure, but fails to integrate the two, which hinders the analysis of system formation and evolution mechanisms [25].
Furthermore, when considering research data, geographical big data is deficient in physical environment information, individual attribute information, and economic information. It also faces the constraint of an independent duality between “Human and land,” which hinders the investigation of the interaction mechanism between individuals and the land in the context of tourism.
Furthermore, in terms of research methodology, data-driven verification is used to validate overarching principles, whereas model-driven research relies on microscopic mechanisms. Nevertheless, there is still ongoing debate regarding the laws and procedures governing the interaction between humans and land in the tourism industry. As of now, there is no universally accepted research framework or research paradigm in place for studying this phenomenon [26]. The presence of these two factors complicates the analysis of the system’s development and evolution mechanism [25].
Proposal of Tourism Sensing Framework
This paper aims to address the limitations of monitoring tourism big data and the challenges associated with applying social sensing in tourism monitoring. To achieve this, the research framework of social sensing is utilized, incorporating tourismspecific variables, resulting in the proposal of a tourism sensing research framework. This article aims to address the limitations of previous research on the sensing of “tourist destinations” and the interaction between tourism “Human and places” by developing a comprehensive research framework based on existing studies. Simultaneously, it presents the concept of social sensing, shifting the focus from individuals and locations to the dimension of time. Enhance and incorporate current tourism data and surveillance systems, with a specific emphasis on examining the geographical development of tourist sites and the tourism sector.
Prioritizing the investigation of individuals, current research predominantly neglects the examination of the correlation between location and individuals. Thus, the framework developed in this article encompasses both the emotional distribution of tourists and the spatial structure of tourism flow, while also emphasizing the importance of the tourist destination. The study focuses on the geographical arrangement of tourism resources and the dynamics of tourism land use, with an emphasis on the spatial distribution of elements within the tourism industry.
Furthermore, previous research mostly concentrates on the spatial distribution and characteristics when it comes to sensing, while neglecting to adequately monitor the process. In order to achieve this objective, the concept of time is incorporated into social sensing, and the forecast of spatial evolution in the tourism business and the sensing of spatial evolution in tourist sites are included.
Furthermore, the current research utilizing geographical big data is deficient in terms of physical environment information, individual qualities, and economic attribute data. Thus, by incorporating geographical data, remote sensing image data, user portrait data, and tourism industry economic attributes, we can extract the physical environment system, individual attribute information, and economic attribute information. This helps to compensate for the limitations of big data in accurately describing the relationship between tourists and places.
The spatial development of tourism sector components and tourist destinations is an intricate system of interaction between humans and the land. The examination of the relationship between humans and the land in the context of tourism is crucial in determining the outcome of spatial development. To gain a comprehensive understanding of the interaction between Human and places in tourism, it is necessary to examine the underlying mechanisms and processes involved. By doing so, we can ensure that the perceived impact of the relationship between Human and places is effectively managed. Thus, the paradigm developed in this paper emphasizes the examination of industrial determinants and the developmental trajectory of tourism sites.
References
- Torres-Delgado A, Saarinen J (2017) Using indicators to assess sustainable tourism development: A review. New research paradigms in tourism geography 31-47.
- Liu Y, Bao JG, Zhu YL (2017) Exploring emotion methods of tourism destination evaluation: A big-data approach. Geographical Res 36(6): 1091-1105.
- Kang Y, Jia Q, Gao S, Zeng X,Wang Y, et al. (2019) Extracting human emotions at different places based on facial expressions and spatial clustering analysis. Transactions in GIS 23(3): 450-480.
- Liu Y, Bao JG, Chen KQ (2017) Sentimental features of Chinese outbound tourists in Australia: big-data based content analysis. Tourism Tribune 32(5): 46-58.
- Li Y, Guo J, Chen Y (2022) A new approach for tourists’ visual behavior patterns and perception evaluation based on multi-source data. J Geo-Inf Sci 24(10): 2004-2020.
- Zhang Shien, Zhang Jie, Han Guo-sheng, Wang Lan, Zhang Hong-lei (2010) Basic Theory of Tourism Flow Spatial Patterns: Problem Analysis and Prospects. Human Geography 25(2): 31-36.
- Jiang YY, Gao J, Guo JM, Xu HB (2024) Big geodata in tourism research: innovative application, disciplinary influence and research prospect. J Geo-Info Sc 26(2): 242-258.
- Fan Z, Zhang F, Loo BP, Ratti C (2023) Urban visual intelligence: Uncovering hidden city profiles with street view images. Proc Natl Acad Sci 120(27): e2220417120.
- Xu X, Zhao L, Liu B, Wu B, Zhong L (2015) Study on perceived image of Chinese tourist cities. Geographical Res 34(7): 1367-1379.
- Deng N, Liu J, Niu Y, Ji WX (2019) Different perceptions of Beijing’s destination images from tourists: An analysis of Flickr photos based on deep learning method. Resour Sci 41(3): 416-429.
- Jiang YY, Deng N, Gao BB, Li Yuan, Li Yunpeng, et al. (2024) A dialectical examination of geo-information science in the field of tourism and recreation. J Geo Info Sci 26(2): 227-241.
- Zheng Y, Zhang Y, Mou N, Makkonen T, Li M, et al. (2024) Selection biases in crowdsourced big data applied to tourism research: An interpretive framework. Tourism Manage 102: 104874.
- Santos F, Almeida A, Martins C, Gonçalves R, Martins J (2019) Using POI functionality and accessibility levels for delivering personalized tourism recommendations. Computers, Environment and Urban Systems 77: 101173.
- Liu Y, Liu X, Gao S, Gong L, Kang C, et al. (2015) Social sensing: A new approach to understanding our socioeconomic environments. Annals of the Association of American Geographers 105(3): 512-530.
- Liu Y, Wang F, Xiao Y, Gao S (2012) Urban land uses and traffic ‘source-sink areas’: Evidence from GPS-enabled taxi data in Shanghai. Landscape and Urban Planning 106(1): 73-87.
- Ye C, Zhang F, Mu L, Gao Y, Liu Y (2021) Urban function recognition by integrating social media and street-level imagery. Environment and Planning B: Urban Analytics and City Sci 48(6): 1430-1444.
- Mitchell L, Frank MR, Harris KD, Dodds PS, Danforth CM (2013) The geography of happiness: Connecting twitter sentiment and expression, demographics, and objective characteristics of place. PloS one 8(5): e64417.
- Yang W, Mu L (2015) GIS analysis of depression among Twitter users. Applied Geography 60: 217-223.
- Zhang F, Zhou B, Liu L, Liu Y, Fung HH, et al. (2018) Measuring human perceptions of a large-scale urban region using machine learning. Landscape and Urban Planning 180: 148-160.
- Guo S, Song C, Pei T, Liu Y, Ma T, et al. (2019) Accessibility to urban parks for elderly residents: Perspectives from mobile phone data. Landscape Urban Planning 191: 103642.
- Liu X, Gong L, Gong Y, Liu Y (2015) Revealing travel patterns and city structure with taxi trip data. J Transport Geography 43: 78-90.
- Kang C, Ma X, Tong D, Liu Y (2012) Intra-urban human mobility patterns: An urban morphology perspective. Physica A: Statistical Mechanics and its Appl 391(4): 1702-1717.
- Zhu D, Zhang F, Wang S, Wang Y, ,Ximeng C, et al. (2020) Understanding place characteristics in geographic contexts through graph convolutional neural networks. Annals of the American Association of Geographers 110(2): 408-420.
- Zhong C, Arisona, SM, Huang X, Batty M, Schmitt G (2014) Detecting the dynamics of urban structure through spatial network analysis. Int J Geograp Info Sci 28(11): 2178-2199.
- Xue LI, Suo-cheng, DONG, Shan-tong, LI (2012) A Summary of Study on the Evolution of Tourism Regional System. Tourism Tribune 27(9): 46-55.
- Yang CY, Huang ZF, Mao WD (2009) On the schools, courses and prospect of complex system evolution theory in tourism areas. Hum. Geogr 24: 66-70.