The rapid growth of tourist-generated content demands scalable and reliable quality assessment methods. This study introduces an LLM-driven framework that combines parameter-efficient fine-tuning and prompt engineering to evaluate content quality accurately and interpretably. Applied to 484,930 reviews from MaFengWo, TripAdvisor, and Ctrip, the approach achieves superior performance (RMSE=0.3040, NDCG@100=0.500, BERTScore=77.95%) with 9 × higher efficiency. Spatial-temporal-semantic analyses reveal platform-specific quality patterns: MaFengWo exhibits prominent spatial centrality and stable temporal cointegration; TripAdvisor demonstrates simplified core-periphery structures with high volatility; Ctrip presents dynamic multicentricity particularly in Shanghai. Two domestic platforms, MaFengWo and Ctrip, expose systematic deficiency on the theme ‘ Decision-making Plan ’ (92.9∼96.4% lacking operational suggestions), while international TripAdvisor emphasizes ‘ Practical Information ’ and ‘ Consumption Activity ’ but 40.76% neglects original viewpoints. Heterogeneous network analysis identifies the behavioral signatures of high-reliability user—preference attachment, quality stability, and profile homogeneity. This work bridges theoretical rigor with operational scalability, demonstrating the potential of LLMs in content governance for digital tourism.

Social issues, AI, and climate change are just a few of the disruptive focuses impacting science. The field of GIScience is well positioned to respond to accelerating disruptions due to the interdisciplinary nature of the field and the ability of GIScience approaches to be used in support of decision-making. This manuscript aims to start a conversation that will establish a research agenda for GIScience in an age of disruptions. We outline three guiding principles: (1) focusing on the relevance and real-world impact of research, (2) adopting systems-based thinking and contextual approaches and (3) emphasizing inclusive practices. We then outline prioritized research areas organized by what topics are important focal areas (Data and Infrastructure, Artificial Intelligence, and Causality and Generalizability), and what approaches to science we should be attentive to (Impactful Open Science, Collaborative and Convergent Science, and through Diverse Participation and Partnerships). We conclude with a call to increase impact by balancing slow science with practical and policy-oriented research. We also recognize that while broad adoption of spatial approaches is a signal of GIScience's success, we should continue to work together to advance core knowledge centered on spatial thinking and approaches.

While many countries are developing appropriate actions towards a greener future and moving towards adopting sustainable mobility activities, the real-time management and planning of innovative transportation facilities and services in urban environments still require the development of advanced mobile data management infrastructures. Novel green mobility solutions, such as electric, hybrid, solar and hydrogen vehicles, as well as public and gig-based transportation resources are very likely to reduce the carbon footprint. However, their successful implementation still needs efficient spatio-temporal data management resources and applications to provide a clear picture and demonstrate their effectiveness. This paper discusses the major data management challenges, open issues, and application opportunities closely related to urban green mobility. Additionally, it reports on recent successful experiences and challenging research questions. Furthermore, it highlights the global benefits one can expect when developing green mobility and emphasizes how mobile data infrastructures and services will play a crucial role in achieving these goals.

Digital systems storing cadastral data in vector format are considered effective due to their ability of offering interactive services to citizens and other land-related systems. The adoption of such systems is ubiquitous, but when adopted, they create two non-compatible systems with paper-based cadastral systems whose information needs to be digitised. This study proposes a new approach that is fast and accurate for transforming paper-based cadastral data into digital systems. The proposed method involves deep-learning techniques of the LCNN and ResNet-50 for detecting cadastral parcels and their numbers, respectively, from the cadastral plans. It also contains four functions defined to speed up transformations and compilations of the cadastral plan’s data in digital systems. The LCNN is trained and validated with 968 samples. The ResNet-50 is trained and validated with 106,000 samples. The Structural-Average-Precision (sAP10) achieved with the LCNN was 0.9057. The Precision, Recall and F1-Score achieved with the ResNet-50 were 0.9650, 0.9648 and 0.9649, respectively. These results confirmed that the new method is accurate enough for implementation, and we tested it with a huge set of data from Tanzania. Its performance from the experimented data shows that the proposed method could effectively transform paper-based cadastral data into digital systems.

Hierarchical graph-based approaches provide valuable abstractions for studying emerging topological structures and favour a better understanding of mobility patterns and similarities. This research introduces a hierarchical similarity measure that applies a series of distances toward a hierarchical graph-based model. This similarity measure is derived from different categories of distances and is experimented with evolving hierarchical graphs extracted from a European maritime mobility dataset.

This paper introduces a graph-based visualization system for representing the vulnerabilities of an ecosystem of norms. Norm dependencies are crawled and extracted from reference normative documents. A series of interactive graphs and chord-based visualisations support the identification and valuations of norm interdependencies and clusters, as well as potential vulnerability propagation paths. The whole approach is applied to ISO 19100 standard series and S-100 geographical and electronic navigation chart standards.

Hierarchical graph-based approaches provide valuable abstractions for studying the topological structures that emerge and a better understanding of mobility patterns at complementary spatial and temporal scales. This research introduces a hierarchical graph-based model to represent and analyse a maritime transportation network at several spatio-temporal and semantic levels, as well as a new hierarchical extension of an accessibility measure. The proposed model is implemented in a graph database using maritime mobility data. The peculiarities of the hierarchical accessibility are computationally evaluated in comparison with non-hierarchical approaches.

Past and current cadastral records are among the most valuable information that different countries need to solve land management and planning problems. However, many countries still face critical challenges in adopting modern temporal cadastral systems, including a sound integration of time constructs, efficient data integration and representation methods in the designed models. This research developed a new temporal GIS model to manage spatial and non-spatial temporal cadastral data, namely cadastral parcels, land-use and land-ownerships. Three-time dimensions defined by decision and valid and transaction times were formulated to qualify parcels data. A hybrid approach fusing on the Base State with Amendment and Space-Time Composite models is used to store significant parcel changes and their relationships in two interdependent sub-databases. We used administrative plot identifiers to associate with land use and ownership records, experiencing distinct temporal variations in the third sub-database within the same main repository. We experimented our model with data from Tanzania, and the results from queries demonstrate that the designed model can store all three temporal cadastral data and track their variations semantically and effectively. This model is very useful for storing cadastral parcels, reasons, events, and the transformed parcels’ values to improve decision-making processes.

This paper introduces a psycho-acoustic experimental setup for the representation of urban soundscapes. The approach combines a series of acoustic measurements and ambisonic recordings made with several sensors that favour the interpretation of biological, geophysical and anthropogenic sounds derived from an urban environment. The experiments realized in the Tunisian city of Sidi Bou Saïd illustrate how such soundscapes can be visualised and interpreted, as well as the feasibility of the whole framework experimented in a real urban environment.

Exploiting semantic information related to human mobility is particularly useful in crowd-sourcing environments where multidimensional data represent human trajectories and contextual information arising in indoor and outdoor spaces. This paper introduces a modelling approach and data manipulation mechanisms that represent semantic trajectories at different levels of abstraction. The objective is to produce a hybrid spatial representation for continuous mobility patterns emerging in indoor and outdoor spaces. This approach is based on a multi-layered graph that represents trajectories derived on the fly according to some given spatio-temporal constraints. The multi-layer graph provides a hierarchy of semantic places that offers several data manipulation capabilities according to given contextual and user-defined criteria.

The search for the most appropriate GIS data model to integrate, manipulate and analyse spatio-temporal data raises several research questions about the conceptualisation of geographic spaces. Although there is now a general consensus that many environmental phenomena require field and object conceptualisations to provide a comprehensive GIS representation, there is still a need for better integration of these dual representations of space within a formal spatio-temporal database. The research presented in this paper introduces a hybrid and formal dual data model for the representation of spatio-temporal data. The whole approach has been fully implemented in PostgreSQL and its spatial extension PostGIS, where the SQL language is extended by a series of data type constructions and manipulation functions to support hybrid queries. The potential of the approach is illustrated by an application to underwater geomorphological dynamics oriented towards the monitoring of the evolution of seabed changes. A series of performance and scalability experiments are also reported to demonstrate the computational performance of the model.

This paper introduces a simplex-based enriched graph data model integrating a discrete and place-based indoor spatial model with a spatial-social network. The proposed model incorporates similarity and relevance measures, exhibited from Q-analysis of simplicial complexes, facilitating data manipulation and revealing latent relations in a spatial-social network. It also uses an indoor-specific metric representing the ease of access to process spatial-social queries in indoor environments. The proposed model’s experimental implementation shows the quantitative advantage of using graph-based representation and the qualitative superiority of simplex-based enrichment in processing spatial-social queries in indoor environments.

Modern and connected mobilities have generated an explosive growth of location-based information. Such location data together with related crowd-sensed information, are noticeably available for humans navigating in both indoor and outdoor spaces. Considering the diversity of such multi-environment spaces, and where mobility occurs, raises several data modelling, management and processing research challenges. This not only implies to develop appropriate database architecture for large streamed data but also to identify the most appropriate data abstractions to model these human trajectories at the semantic level. While recent approaches often considered this issue using common stops and moves model, this does not completely cover the multi-dimensional contextual information that arises for humans navigating through indoor and outdoor spaces. This paper introduces a model of semantic trajectories evolving in both indoor and outdoor spaces, and cross-related with contextual information. This model defines a semantic trajectory considering multiple collaborative data semantics at different abstraction levels, and where trajectory segmentation relies on evolving semantic values. This enables (i) a unified indoor and outdoor spatial representation for trajectory annotation and (ii) multidimensional data integration and management. The final aim is to support semantic querying for a better understanding of human mobilities in urban environments.

The COVID-19 global pandemic emerged in the late 2019 causing so far a massive global health disruption with many fatalities and huge economy impact, enforcing most if not all governments to a global lockdown. Besides the battle on the medical front-line, governments and the industry also massively explored the deployment of information and communication technologies to track and curb the spread of the virus. On the front-line of these efforts, have been the so-called Mobile Contact Tracing Applications (MCTA). These refer to mobile apps that exploit the rich ecosystem of mobile sensors (e.g., location, proximity) as well as social networks to facilitate the process of identification of persons who may have been previously into contact with a covid infected person and subsequent collection of further information about these contacts. Although MCTA can in theory help governments fight the rapid spread of diseases like COVID-19, there are important privacy considerations and many claim that these technologies will put in place a massive global surveillance infrastructure that will survive even when a vaccine for the COVID-19 disease has been found. This panel aims to discuss the major challenges and open topics surrounding MCTA. The panelists are expected to bring wealth of experience and vision from the academic, governmental and industrial sector to answer a set of challenging questions that are currently open to public debate as well as the global benefits one can expect when fighting the COVID-19 spread.

The experimental research developed in this paper introduces a hybrid temporal GIS representation for studying the dynamics of a coastal seabed. The approach is based on a dual temporal GIS data model that combines the object and field views of space. The first concept is the one of an object-field defined as a field in which each location is associated to one or more geographic objects type. The second key concept is the field-object defined as an object with internal heterogeneity conceptualized as a field. The main idea behind this approach is to provide a flexible representation that supports field and object evolutions. A series of spatio-temporal queries have been categorized and specified on top of the hybrid representation and shows the interest of the combination of the field and object abstractions at the data manipulation level. The approach has been applied to a coastal data environment, and implemented within the PostgreSQL RDBMS and its spatial extension PostGIS.

Computer networks are ubiquitous systems growing exponentially with a predicted 50 billion devices connected by 2050. This dramatically increases the potential attack surface of Internet networks. A key issue in cyber defense is to detect, categorize and identify these attacks, the way they are propagated and their potential impacts on the systems affected. The research presented in this paper models cyber attacks at large by considering the Internet as a complex system in which attacks are propagated over a network. We model an attack as a path from a source to a target, and where each attack is categorized according to its intention. We setup an experimental testbed with the concept of honeypot that evaluates the spatio-temporal distribution of these Internet attacks. The preliminary results show a series of patterns in space and time that illustrate the potential of the approach, and how cyber attacks can be categorized according to the concept and measure of entropy.

Fictive motion (e.g. ‘The highway runs along the coast’) is a pervasive phenomenon in language that can imply both a static and a moving observer. In a corpus of alpine narratives, it is used in three types of spatial descriptions: conveying the actual motion of the observer, describing a vista and communicating encyclopaedic spatial knowledge. This study takes a knowledge-based approach to develop rules for automated extraction and classification of these types based on an annotated corpus of fictive motion instances. In particular, we identify the differences in the set of concepts involved into the production of the three types of descriptions, followed by their linguistic operationalization. Based on that, we build a set of rules that classify fictive motion with an overall precision of 0.87 and recall of 0.71. The article highlights the importance of examining spatially rich, naturally occurring corpora for the lines of work dealing with the automated interpretation of spatial information in texts, as well as, more broadly, investigation of spatial language involved into various types of spatial discourse.

Automatic Identification System (AIS) provides realtime information of moving vessels in the sea of the whole world. The AIS data can be exploited for vessel tracking, collision avoidance, traffic management and maritime surveillance. Although the AIS data accumulated from vessels over the area of interest may become a very large amount, clustering of these AIS data leads to benefit of knowledge discovery of maritime traffic and detection of abnormal events. On the other side, in the realm of machine learning and natural language processing, topic model provides novel approaches for extracting the topics that are implicit in massive and unstructured collection of documents. The most common implementation of topic model is LDA algorithm. From these facts, we are seized to apply topic model to solve route extraction problem. In this paper, we will describe our approach for route extraction from AIS data by using vector quantization and topic model at first. Then we will show some experimental results of route patterns extraction with a practical AIS data set.

S.192-197

The continuous development of Spatial Data Infrastructures (SDI) provides a favourable context for environmental management and planning. However, it appears that the actual contribution of SDIs should also depend on the correlation between users’ expectations and the services delivered to them. Several studies have addressed some organizational, methodological and technological aspects of the development of SDIs. However, only a few studies have, to the best of our knowledge, studied SDI use at large. This article introduces a methodological approach oriented towards the study of the relationship between SDIs and the users interacting with them as part of their professional practices. Our study is applied to coastal zone management and planning in France. This approach combines structural and data flow modelling. The former is based on Social Network Analysis (SNA) and the latter on Data Flow Diagrams (DFD). This modelling approach has been applied to an online questionnaire and semi-structured interviews. The results identify the SDIs, geographical data flows and institutional levels implied in French coastal zone management and planning.

The representation of human knowledge extracted from navigations in natural environments is still a research challenge for spatial cognition and computer science. When acting in natural environments people often use verbal route descriptions or sketch maps to transmit their knowledge of the environment, and some of the actions performed. The research developed in this paper introduces a modeling and computational approach using verbal descriptions of human navigating in a natural environment. The objective is to extract the semantic and spatial knowledge emerging from the verbal route descriptions. A formal and semantic model is introduced with a series of rules that merge different route descriptions. The semantic network constructed presents a global view of the route descriptions, and is used to generate a map representation from them. The whole approach is illustrated by a case study.

Social networks provide rich data sources for analyzing people journeys in urban environments. This paper introduces a trusted path system that helps users to find their routes based in two criteria: low crime rate and no theft report. These data are obtained from two complementary sources: geo-tagged tweets from the social network Twitter, and an official database given by the Police of Mexico City. Recommended paths are computed automatically from these data sources by a complementary application of social mining techniques, Bayes algorithm and an adaptation of the Dijkstra algorithm. This system can be also used to identify the probability that an event occurs in specific locations and times. A proof of concept of the system is illustrated through two example scenarios.

Social networks provide rich data sources for analyzing people activities. This paper introduces a mobile recommender system that suggests places to visit to tourists acting in the city of Mexico. The system developed generates itineraries based on the implicit users' behaviors. Recommendations are automatically extracted and analyzed from Twitter thanks to the application of Bayes and Tree algorithms. Suggested itineraries are cross-analyzed to take into account user profiles and preferences. The recommender system provides an augmented reality navigation system that suggests itineraries to the users according to some places of interest. The preliminary prototype developed is an Android app so-called "Turicel Social".

When it comes to characterize the distribution of ‘things’ observed spatially and identified by their geometries and attributes, the Shannon entropy has been widely used in different domains such as ecology, regional sciences, epidemiology and image analysis. In particular, recent research has taken into account the spatial patterns derived from topological and metric properties in order to propose extensions to the measure of entropy. Based on two different approaches using either distance-ratios or co-occurrences of observed classes, the research developed in this paper introduces several new indices and explores their extensions to the spatio-temporal domains which are derived whilst investigating further their application as global and local indices. Using a multiplicative space-time integration approach either at a macro or micro-level, the approach leads to a series of spatio-temporal entropy indices including from combining co-occurrence and distances-ratios approaches. The framework developed is complementary to the spatio-temporal clustering problem, introducing a more spatial and spatio-temporal structuring perspective using several indices characterizing the distribution of several class instances in space and time. The whole approach is first illustrated on simulated data evolutions of three classes over seven time stamps. Preliminary results are discussed for a study of conflicting maritime activities in the Bay of Brest where the objective is to explore the spatio-temporal patterns exhibited by a categorical variable with six classes, each representing a conflict between two maritime activities.

Route planning is an important problem for many real-time applications in open and complex environments. The maritime domain is a relevant example of such environments where dynamic phenomena and navigation constraints generate difficult route finding problems. This paper develops a spatial data structure that supports the search for an optimal route between two locations while minimizing a cost function. Although various search algorithms have been proposed so far (e.g. breadth-first search, bidirectional breadth-first search, Dijkstra’s algorithm, A*, etc.), this approach provides a bidirectional dynamic routing algorithm which is based on hexagonal meshes and an iterative deepening A* (IDA*) algorithm, and a front to front strategy using a dynamic graph that facilitates data accessibility. The whole approach is applied to the context of maritime navigation, taking into account navigation hazards and restricted areas. The algorithm developed searches for optimal routes while minimizing distance and computational time.

This paper introduces a graph-based and structural model for the representation of land spaces. We develop a spatial model that integrates three complementary abstractions (i.e., parcels, buildings, roads) that provide a spatial and structural representation. The modeling approach retains different categories of topological relations between parcels, buildings and roads, thus generating different graphs whose properties are evaluated and computed using graph-based operators. The union of these graphs generates a connected spatial graph where buildings are closely associated to parcels and the road network, then providing many opportunities for structural analysis.

This paper introduces an augmented-reality system that provides navigation facilities, generation of itineraries and services delivery. The approach offers the possibility of combining real sceneries with digital representations of places of interest and services for a given itinerary. The first level of the approach supports the identification of a given place based on Augmented reality (AR), offering additional information (images and description) of that place. The second level generates navigation itineraries based on semantic Web services, user profiles and recommendations obtained from tourism sources. The experimental setup integrates smartphones with digital compass, GPS, camera and accelerometer. The framework has been experimented in Mexico downtown in the historical center "Zocalo". The applications are available in App Store and Google Play Store called "Turicel aumentado" and "Turicel2", respectively.

Continuous location-dependent queries can be considered as key elements for the development of different categories of location-based and context-aware services. However, most work on location-dependent query processing has been mainly oriented towards outdoor environments. This paper studies location-dependent and context-aware queries over moving objects in indoor environments (e.g., houses, commercial malls, etc.), with a special focus on navigation-related queries (i.e., mainly path search and range queries). A hierarchical and context-dependent spatial data model is firstly presented, which leads to the consideration of other contextual dimensions besides the location of the involved entities, such as time and user profiles. Two algorithms for continuous processing of path and range queries on top of this modelling approach are introduced. The former performs a hierarchical and incremental path search for the continuous processing of path queries, and applied to both static and moving objects. The latter presents an incremental approach for continuous range queries, which performs a hierarchical network expansion around the initial query point and implements a mechanism to update the initial search tree based on user's movements.

Indoor environments offer many possibilities for the development of navigation-aided systems and location-based services. This paper introduces an experimental setup that combines navigation facilities with augmented reality, and which is applied to two museums in the city of Mexico. The approach is based on a semantic model of a museum environment that reflects its organization and spatial structure. The experimental setup combines augmented reality, digital compass devices with smartphones. While several constraints reduce interaction capabilities among exhibitions and visitors, augmented reality offers the possibility of relaxing these constraints by combining real sceneries with digital representations. This enhances interactions between users and objects of interest pointed by the users, where additional multimedia information on the collections presented is available on demand.

While conventional GIS maps have long been a privileged way for the integration and diffusion of geographical information, novel forms of representation and description of urban and natural environments are nowadays emerging. In particular, verbal and textual descriptions of landscapes are progressively considered as alternative modeling resources for GIS. The research presented in this paper introduces a salience-based approach whose objective is to identify the noticeable entities of a natural landscape description. The model is based on a structural analysis of a given description, where salient entities are identified at the linguistic and structural levels. Salient entities are also spatially qualified according to their relative location with respect to a given observer.

This paper introduces an ant-based colony system for the representation of a verbal route description. It is grounded on a natural metaphor that mimics the behavior of ant colonies. While conventional ant-based algorithms are based on the optimization of path strategies on an existing network, the approach presented in this paper differs in the way the network is dynamically derived during the optimization process, and evaluated according to its degree of match regarding the semantics exhibited by a verbal route description. The algorithm is applied to a route searching process in a natural environment, and studied in terms of its performance capabilities.