Content

Xiaoyue Ma, Pengzhen Xue, Nada Matta, Reconstruction of Crisis Knowledge Ontology by Integrating Temporal-Spatial Analysis in:

International Society for Knowledge Organziation (ISKO), Marianne Lykke, Tanja Svarre, Mette Skov, Daniel Martínez-Ávila (Ed.)

Knowledge Organization at the Interface, page 499 - 501

Proceedings of the Sixteenth International ISKO Conference, 2020 Aalborg, Denmark

1. Edition 2020, ISBN print: 978-3-95650-775-5, ISBN online: 978-3-95650-776-2, https://doi.org/10.5771/9783956507762-499

Series: Advances in Knowledge Organization, vol. 17

Bibliographic information
Xiaoyue Ma – Xi'an Jiaotong University, China Pengzhen Xue – Xidian University, China Nada Matta – Troyes University of Technology, France Reconstruction of Crisis Knowledge Ontology by Integrating Temporal-Spatial Analysis Abstract: In this paper the restructuring of crisis knowledge by integrating temporal-spatial analysis was proposed and considered into ontology construction. It aims to explain the temporal-spatial features and composite effects of crisis knowledge, and then implement a fine-grained reconstruction model based on ontology. 1.0 Introduction Ontology is one of the common methods of conceptual crisis knowledge organization because of its meaningful contribution onto the sustainable knowledge management and intelligent decision making (Mescherin et al. 2012; Matta et al. 2012). However, former researches for the ontology-based crisis knowledge organization were interested more in crisis types and attributes while ignoring the real-time dynamics of information during the emergency rescue (Moehrle 2012; Xu, Nyerges, and Nie 2013). Therefore, in this paper the dynamic organization of crisis knowledge will be analyzed and restructured relied on their temporal-spatial features by using ontology. The innovations of this study are as follows. First, temporal and spatial factors are segmented according to sequences and scenes, based on which the cross-effects of their dynamic changes are analyzed. Second, a fine-grained dynamic knowledge organization of feature units from the perspective of composite temporal-spatial relationships is proposed, which is supposed to express the dynamic semantic structure more accurately. 2.0 Reconstruction of fine-grained crisis ontology for integrating temporal-spatial features This section will introduce how to reconstruct crisis knowledge by integrating temporal-spatial features. The research framework is shown as the figure below (seen in Figure 1): Figure 1: Research framework of reconstruction with integrating temporal-spatial features 500 2.1 Analysis of temporal and spatial features of crisis knowledge In this study we divide crisis knowledge into two categories: dynamic knowledge and static knowledge. Static knowledge represents the information that does not change during the whole development of the crisis, while the dynamic knowledge represents the information with characteristics of multi-phase and discontinuity. Since the attributes of static knowledge are all fixed values, the corresponding temporal and spatial attributes could be simply labeled and added. While for dynamic crisis knowledge, we need to divide the time series into multiple time regions with short duration and high granularity (Pohl, Bouchachia, and Hellwagner 2018). Similarly, we divide the space into multiple scenes with small space and high density. The classification of disaster levels is applied to indicate the severity of disasters in a fixed area (Saoutal, Cahier, and Matta 2014). The correlation analysis explores the interaction between temporal and spatial characteristics, such as the division of time zones will affect the regional division of disaster levels. For example, in the same disaster area, the severity of disasters must be different in the crisis development time zone and the crisis recovery time zone. The integration research of temporal-spatial characteristics explores the influence of temporal and spatial characteristics on the organization of crisis knowledge. For example, we use the division of time zones and disaster levels to determine whether a region has been affected by a crisis and to what extent so as to determine whether this region is an area of crisis rescue or crisis supply. 2.2 Fine-grained ontology reconstruction based on temporal-spatial composite features Combined with the analysis of temporal-spatial features, a fine-grained crisis knowledge ontology model could be implemented from the perspective of the temporalspatial correlation. The temporal and spatial relationships represent respectively the temporal and spatial attributes of crisis knowledge; while the semantic relation indicates the crisis knowledge structure. The crisis knowledge ontology model integrating the temporal-spatial features analysis is shown in Figure 2. Figure 2 Schematic representation of fine-grained ontology reconstruction 501 3.0 Conclusion This study proposes a fine-grained knowledge reconstruction by analyzing the temporal-spatial composite features of crisis knowledge. It solves the problems of inflexible structure and lack of dynamic integration in crisis knowledge organization. Meanwhile it also suggests new methods and ideas for the ontology-based construction of crisis information resources and real-time crisis management, which could be further improved by knowledge graphs for example. Since it is work-in-progress research, the evaluation or instance verification of this ontology construction will be performed in our future studies. References Matta, Nada, Sophie Loriette, Mohammed Sediri, Jean Marc Nigro, Yann Barloy, Jean Pierre Cahier, and Alain Hugerot. 2012. “Crisis Management Experience Based Representation Road Accident Situations.” In 2012 International Conference on Collaboration Technologies and Systems (CTS), Denver, CO, 61-67. doi: 10.1109/CTS.2012.6261028. Mescherin, Sergey, Igor Kirillov, and Stanislav Klimenko. 2012. “Leveraging UML and Concept Maps for Constructing Crisis Management Ontology.” In 2012 International Conference on Cyberworlds, Darmstadt, 2012, 130-136. doi: 10.1109/CW.2012.25. 130-136. Moehrle, Stella. 2012. “Generic Self-Learning Decision Support System for Large-Scale Disasters.” In Proceedings of the 9th International ISCRAM Conference –Vancouver, Canada, April 2012, edited by Leon Rothkrantz, Jozef Ristvej, and Zeno Franco. Vancouver : Simon Fraser University. Pohl, Daniela, Abdelhamid Bouchachia, and Hermann Hellwagner. 2018. “Batch-Based Active Learning: Application to Social Media Data for Crisis Management.” Expert Systems with Applications 93: 232-244. Saoutal, Amina, Jean-Pierre Cahier, and Nada Matta. 2014. “Modeling the Communication Between Emergency Actors in Crisis Management.” In 2014 International Conference on Collaboration Technologies and Systems (CTS), Minneapolis, MN, 545-552. Xu, Jinghai, Timothy L. Nyerges, and Gaozhong Nie. 2013. “Modeling and Representation for Earthquake Emergency Response Knowledge: Perspective for Working with Geo-Ontology.” International Journal of Geographical Information Science 28, no. 1: 185-205.

Chapter Preview

References

Abstract

The proceedings explore knowledge organization systems and their role in knowledge organization, knowledge sharing, and information searching.

The papers cover a wide range of topics related to knowledge transfer, representation, concepts and conceptualization, social tagging, domain analysis, music classification, fiction genres, museum organization. The papers discuss theoretical issues related to knowledge organization and the design, development and implementation of knowledge organizing systems as well as practical considerations and solutions in the application of knowledge organization theory. Covered is a range of knowledge organization systems from classification systems, thesauri, metadata schemas to ontologies and taxonomies.

Zusammenfassung

Der Tagungsband untersucht Wissensorganisationssysteme und ihre Rolle bei der Wissensorganisation, dem Wissensaustausch und der Informationssuche. Die Beiträge decken ein breites Spektrum von Themen ab, die mit Wissenstransfer, Repräsentation, Konzeptualisierung, Social Tagging, Domänenanalyse, Musikklassifizierung, Fiktionsgenres und Museumsorganisation zu tun haben. In den Beiträgen werden theoretische Fragen der Wissensorganisation und des Designs, der Entwicklung und Implementierung von Systemen zur Wissensorganisation sowie praktische Überlegungen und Lösungen bei der Anwendung der Theorie der Wissensorganisation diskutiert. Es wird eine Reihe von Wissensorganisationssystemen behandelt, von Klassifikationssystemen, Thesauri, Metadatenschemata bis hin zu Ontologien und Taxonomien.