In this study, information on water leaks and water quality accidents was extracted and analyzed using big data analysis techniques. A web crawling technique for extracting big data news on water leakage and water quality accidents was applied, and an algorithm was presented as a procedure to obtain...
In this study, information on water leaks and water quality accidents was extracted and analyzed using big data analysis techniques. A web crawling technique for extracting big data news on water leakage and water quality accidents was applied, and an algorithm was presented as a procedure to obtain accurate leak and water quality accident news. In addition, a data analysis technique suitable for water leakage accident information analysis was developed so that additional information such as the cause of occurrence, the point of occurrence, and the extent of damage can be obtained from the extracted leak accident article. Lastly, in the case of a large-scale water quality accident, temporal patterns such as accident recognition, accident spread, accident response, and accident resolution are shown. That is, the analysis of the development of water quality accidents through key keywords and sentiment analysis for each stage was carried out in detail based on case studies, and the meanings were analyzed and derived.
The final goals of this study is to collect and analyze information related to water leakage and water quality that cannot be easily analyzed using news search results from portals that people can easily access. Value extraction through big data-based leak analysis has the primary goal of extracting meaningful values through comparison with existing water supply statistical results. It can be used to determine the service level. In the case of water quality accident big data analysis, water quality accidents have a direct impact on consumer confidence, so the purpose is to analyze the articles that reflect the consumer's psychological state step by step and to acquire high-quality values.
The significance of the thesis depending on the methodology presented in this study and the results of application of the methodology is as follows. First, through the results of web crawling analysis, it was numerically confirmed that information on the disclosure of the media about water leakage and water quality accidents in the water supply system, response and recovery in case of an accident, was not provided quickly. This means that the success factor of digital transformation according to the acceleration of the 4th industrial revolution in the operation and maintenance of water supply facilities can start with the transparent disclosure of information. In other words, two-way communication with consumers through transparent disclosure of accident situations is absolutely necessary, and through this, it is possible to determine and understand consumer-centered service level rather than supplier-oriented service supply.
Second, this study shows that it is possible to extract additional information about water leak accidents through news articles in a situation where disclosure of information that directly affects consumers. In other words, it was possible to extract the value of the cause of the leak accident, the size of the damage, and the degree of spread of the damage from news articles, which are not presented in the water supply statistics. This can be said to show the applicability of real-time web crawling analysis to the water supply system for real-time accident analysis, recognition, and response in the current situation where disclosure of information on crisis situations is limited.
Finally, it was confirmed that the tone of news articles and media reports about water quality accidents with long-term damage in the event of an accident and the degree of consumer's satisfaction clearly changed over time. This suggests the need to prepare consumer-centered policies to increase consumer positivity, although quick restoration of facilities is also very important in the development of water quality accidents from the supplier's point of view. In other words, since there is a limit to “zero” water quality accidents in the case of the water supply system, it means that if a similar water quality accident occurs in the future, it is necessary to recognize and respond to accidents faster, and to prepare a compensation system for entering the compensation stage.
Based on the results of this study, future research needs to analyze the difference in information disclosure between special metropolitan cities and general local governments through additional local government applications. In addition, there is a need for advanced research that can derive additional classification criteria for the causes of leaks and water quality accidents and link the analysis results based on specialized terms in the water supply field rather than general terms used in news. In addition, it is necessary to analyze the cases of various water leakage accidents and water quality accidents to classify and analyze the development of accidents according to the cause in detail.
In this study, information on water leaks and water quality accidents was extracted and analyzed using big data analysis techniques. A web crawling technique for extracting big data news on water leakage and water quality accidents was applied, and an algorithm was presented as a procedure to obtain accurate leak and water quality accident news. In addition, a data analysis technique suitable for water leakage accident information analysis was developed so that additional information such as the cause of occurrence, the point of occurrence, and the extent of damage can be obtained from the extracted leak accident article. Lastly, in the case of a large-scale water quality accident, temporal patterns such as accident recognition, accident spread, accident response, and accident resolution are shown. That is, the analysis of the development of water quality accidents through key keywords and sentiment analysis for each stage was carried out in detail based on case studies, and the meanings were analyzed and derived.
The final goals of this study is to collect and analyze information related to water leakage and water quality that cannot be easily analyzed using news search results from portals that people can easily access. Value extraction through big data-based leak analysis has the primary goal of extracting meaningful values through comparison with existing water supply statistical results. It can be used to determine the service level. In the case of water quality accident big data analysis, water quality accidents have a direct impact on consumer confidence, so the purpose is to analyze the articles that reflect the consumer's psychological state step by step and to acquire high-quality values.
The significance of the thesis depending on the methodology presented in this study and the results of application of the methodology is as follows. First, through the results of web crawling analysis, it was numerically confirmed that information on the disclosure of the media about water leakage and water quality accidents in the water supply system, response and recovery in case of an accident, was not provided quickly. This means that the success factor of digital transformation according to the acceleration of the 4th industrial revolution in the operation and maintenance of water supply facilities can start with the transparent disclosure of information. In other words, two-way communication with consumers through transparent disclosure of accident situations is absolutely necessary, and through this, it is possible to determine and understand consumer-centered service level rather than supplier-oriented service supply.
Second, this study shows that it is possible to extract additional information about water leak accidents through news articles in a situation where disclosure of information that directly affects consumers. In other words, it was possible to extract the value of the cause of the leak accident, the size of the damage, and the degree of spread of the damage from news articles, which are not presented in the water supply statistics. This can be said to show the applicability of real-time web crawling analysis to the water supply system for real-time accident analysis, recognition, and response in the current situation where disclosure of information on crisis situations is limited.
Finally, it was confirmed that the tone of news articles and media reports about water quality accidents with long-term damage in the event of an accident and the degree of consumer's satisfaction clearly changed over time. This suggests the need to prepare consumer-centered policies to increase consumer positivity, although quick restoration of facilities is also very important in the development of water quality accidents from the supplier's point of view. In other words, since there is a limit to “zero” water quality accidents in the case of the water supply system, it means that if a similar water quality accident occurs in the future, it is necessary to recognize and respond to accidents faster, and to prepare a compensation system for entering the compensation stage.
Based on the results of this study, future research needs to analyze the difference in information disclosure between special metropolitan cities and general local governments through additional local government applications. In addition, there is a need for advanced research that can derive additional classification criteria for the causes of leaks and water quality accidents and link the analysis results based on specialized terms in the water supply field rather than general terms used in news. In addition, it is necessary to analyze the cases of various water leakage accidents and water quality accidents to classify and analyze the development of accidents according to the cause in detail.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.