A Case Study on Spatio-Temporal Data Mining of Urban Social Management Events Based on Ontology Semantic Analysis

Shaohua Wang, Xianxiong Liu, Haiyin Wang, Qingwu Hu
2018 Sustainability  
The massive urban social management data with geographical coordinates from the inspectors, volunteers, and citizens of the city are a new source of spatio-temporal data, which can be used for the data mining of city management and the evolution of hot events to improve urban comprehensive governance. This paper proposes spatio-temporal data mining of urban social management events (USMEs) based on ontology semantic approach. First, an ontology model for USMEs is presented to accurately extract
more » ... effective social management events from non-structured UMSEs. Second, an explorer spatial data analysis method based on "event-event" and "event-place" from spatial and time aspects is presented to mine the information from UMSEs for the urban social comprehensive governance. The data mining results are visualized as a thermal chart and a scatter diagram for the optimization of the management resources configuration, which can improve the efficiency of municipal service management and municipal departments for decision-making. Finally, the USMEs of Qingdao City in August 2016 are taken as a case study with the proposed approach. The proposed method can effectively mine the management of social hot events and their spatial distribution patterns, which can guide city governance and enhance the city's comprehensive management level. information database of massive municipal administration departments and analyzing the daily behavior patterns of urban residents are important for urban sustainable development. The spatial distribution characteristics of social security problems and the urban inner space structure can provide decisive support for government departments in providing social management content based on urban production, economy, society, culture, and population management. The data mining of human activities and urban social management events from the city management of mining has become a hot research topic for the urban social management [20] [21] [22] [23] . Noulas et al. [24, 25] collected tens-of-millions of user check-in data to analyze the user history, moving trajectory for the prediction of the future migration trend of users, and then presented a user interest site recommendation. Ji et al. [26] proposed a themed street clustering method to detect the themed streets of a specific region with the user's mobile phone data from social networks. Farhad and Laylavi [27] designed a multi-elemental location inference method with the geotagged data from Twitter and tried to predict the location of tweets to provide auxiliary data for emergency response. Hu et al. [28] proposed an urban commercial area mining and analysis approach by crawling location-based check-in data from social networks such as Weibo to provide reliable decision-making support in urban planning and economic development. Wang et al. [29] designed a POI significance calculation algorithm using the check-in data from social networks. They analyzed the behavior rules of users, and then studied the distribution rules of urban landmarks on the spatial level, which can be well applied in the intelligent urban management and smart city services. With the diversity of data sources, for a wide variety of urban social management data, domestic and foreign scholars have designed a variety of analytical methods applied to different areas of urban social management. Zhang et al. [30] used the Markoff forecast model to predict the urban heat island proliferation tendency and provided the decision-making support to mitigate an urban heat island. Kazak [31] integrated scenario analysis, land use modelling and GIS for the assessment of areas for the potential exposure to the Urban Heat Island (UHI) effect, which can be used for the decision making of urban management. Ai [32] established a BP neural network model to forecast the development trend analysis of haze weather using the historical data of 2.5 PM. Zhao et al. [33] analyzed the two-magnitude five pollutant data and researched and analyzed the winter haze event of the North China Plain and its mechanism. Liu et al. [34] constructed the gray Markov chain model, applied it in the traffic volume forecast domain, and realized the traffic volume high accuracy forecast. Das and Winter [35] designed a hybrid knowledge-driven framework, which integrates fuzzy logic and neural networks to analyze vehicle GPS trajectory data and achieve the real-time detection of city traffic patterns; the framework is of great significance to the traffic and transportation planning work of the city. Deng [36] extracted the law of travel behaviors of residents by analyzing people's travel trajectory data. Using the residents' travel habits, they forecast the traffic demand of the city and provide theoretical support for the traffic control department in urban transportation planning. Bergman and Oksanen [37] combined the motion track data and Open Street Map (OSM) and applied them in the automatic travel route planning. Zhang et al. [38] analyzed the various areas of city residents in the travel law and in different periods by processing urban taxi track data in time-sharing segmentation to obtain information from all city residents who commute. Ishikawa and Fujinami [39] collected a large number of mobile phone users who upload travel data and identified the user's circumvention of certain roads through a large number of pedestrian trajectories. They achieved the detection of abnormal roads, such as road pavement cracks, holes, and other issues. Numerous studies show that the spatio-temporal data mining based on social media data and urban management has been fully applied in various fields of city management, such as emergency response [17, 40] , urban commercial zone and landmark detection for city planning [38, 39] , environment monitoring [38-40], traffic planning [41-44] and road maintenance [45] etc. At present, most of the spatio-temporal data mining researches of urban management are based on indirect data, such as social media data; geo-tagged check-in data; travel data from buses, taxis and subways; cell phone calling data etc., which can only analyze the pattern of a certain phenomenon Sustainability 2018, 10, 2084 3 of 24 in social management from one side [46] [47] [48] [49] [50] . The results of indirect spatio-temporal data mining in urban management have some limitations. For example, it can only reflect a small point of the social comprehensive treatment, and the effectiveness of the results needs to be verified through the actual situation. In the process of smart city construction, information technology and mobile internet have been introduced into the field of social management and comprehensive control [51, 52] . Thus, the real time collection and analysis of various events during the social management can be generated on time from the Smart City platform. In city management, the primary-level staff and volunteers can obtain a large number of firsthand information such as the status of infrastructure services, public security, disputes and other management logs, which have geographical coordinates. These geotagged social management events become direct spatio-temporal data in urban social management. The data mining results are more reliable than indirect data, do not need verification, and can provide better social management and comprehensive control in decision services of city management. Therefore, how to make good use of spatio-temporal data from urban social management to explore the existing problems in current social management and comprehensive control, is of great significance. It can help relevant city departments adjust the social management policies and enhance the ability and level of urban management. This paper takes the spatio-temporal data of the urban social management events in the Huangdao District of Qingdao city as the research sample to dig out the spatial distribution pattern and the event distribution pattern of hot events in social management, such as the status of infrastructure services, social security, production safety, disputes, and other incidents. Moreover, analyzing the internal cause and external expression through spatiotemporal visualization to provide decision support for the social management and comprehensive control of the city.
doi:10.3390/su10062084 fatcat:5ve275nadjasvhtubzz7fp4gxu