• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.179-188
• /
• 2023

Recently, fake news disguises the form of news content and appears whenever important events occur, causing social confusion. Accordingly, artificial intelligence technology is used as a research to detect fake news. Fake news detection approaches such as automatically recognizing and blocking fake news through natural language processing or detecting social media influencer accounts that spread false information by combining with network causal inference could be implemented through deep learning. However, fake news detection is classified as a difficult problem to solve among many natural language processing fields. Due to the variety of forms and expressions of fake news, the difficulty of feature extraction is high, and there are various limitations, such as that one feature may have different meanings depending on the category to which the news belongs. In this paper, emotional change patterns are presented as an additional identification criterion for detecting fake news. We propose a model with improved performance by applying a convolutional neural network to a fake news data set to perform analysis based on content characteristics and additionally analyze emotional change patterns. Sentimental polarity is calculated for the sentences constituting the news and the result value dependent on the sentence order can be obtained by applying long-term and short-term memory. This is defined as a pattern of emotional change and combined with the content characteristics of news to be used as an independent variable in the proposed model for fake news detection. We train the proposed model and comparison model by deep learning and conduct an experiment using a fake news data set to confirm that emotion change patterns can improve fake news detection performance.

• Journal of Convergence for Information Technology
• /
• v.12 no.3
• /
• pp.85-107
• /
• 2022

This study is to analyze the induced effect, network connectivity, and network visualization of the water transportation industry on the overall economy in relation to all industries. For this, various inducement coefficients of the water transportation industry are analyzed using industry linkage analysis and unit structure matrix, and network visualization analysis is performed using network connectivity and NetDraw using Ucinet 6 that utilizes unit structure matrix and inverse matrix function. As a result of the study, analysis results of input coefficient, production inducement coefficient, value-added inducement coefficient, and inter-industry chain effect were presented as various inducement coefficients in the water transportation industry. content was presented. Through this study, the current position and status of the water transportation industry and its relationship with all industries were confirmed, and the strategic relationship with which industries it should be presented was presented. In the future, it is necessary to further analyze the current status and trends of various induced effects, connectivity (centrality), and network visualization analysis using industry-related analysis published since the 2000s.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.3
• /
• pp.774-780
• /
• 2010

USN(Ubiquitous Sensor Network) is a core infrastructure that u-life use to enable the realization in the ubiquitous society through various services of area such as u-city, u-Health. Therefore, we need a research for domestic standards to establish USN technique. Currently, status of USN standards is most standard and research that it is a technology for sensor node implementation and a protocol for energy-efficient communication and interlock with existing network. But, Standard and research for sensor network and integration management of heterogeneous sensor networks for USN application and sensing data management and USN database structure definition such as application and middleware is weak level. In this paper, we researched for standard development of domestic a sensor network and the relevant standard analysis to configure SWE(Sensor Web Enablement) of OGC(Open Geospatial Consortium) for standarded plattform technology. Also we researched that it's a connection between domestic ITA(Telecommunications Technology Association) standards and SWE Standard.

• The Journal of Korean Association of Computer Education
• /
• v.16 no.2
• /
• pp.61-68
• /
• 2013

SNS is a social networking service that helps people to have a two-way communication, manage their personal relationships and share information. The domestic and international SNS markets have attained a steady growth, and their growth is being more accelerated recently. Under these circumstances, immature students are more likely to show negative cyber behavior. This study attempted to analyze the relationship between the use of SNS, motives of SNS use, the use of active SNS functions, SNS-dependency and views in SNS and negative SNS behaviors among elementary and middle school students. For this, negative cycber behaviors are classified into four stages depending on the severity, for each of which distribution of factors is investigated and the combination of factors to determine each stage is obtained through association rule analysis. As a result, it is found that 85% of the students rarely show negative cyber behaviors, stealing personal information and contacting with strangers are the most frequent negative behaviors, and students with a great dependency on SNS are highly probable to show negative behaviors.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.10
• /
• pp.255-260
• /
• 2020

In this paper, I propose an efficient brand identity strategy by topic modeling the Instagram posts, one of SNS(Social Network Service) having more than 1billion world-wide and 500 million daily users. Since the 92% age groups of the Instagram is 18~50 years old (59% 18~29y and 33% 30~49), I set research analysis target three mobile commerce sites to dress and cosmetics sales sites that sale apparels cosmetics and gadgets that recently opened and have operated marketing on diverse channel including SNS. By topic modeling SNS posts for 6 months after launching the site that tagged each m-commerce site brand name or company name, I validate companies' brand identity strategy works effectively and suggest moderation of strategy for brand image. As a result, I found one of three mobile commerce site has different brand image by users and need different identity set up.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.117-127
• /
• 2020

Recently, proving insurance fraud has become increasingly difficult because it occurs intentionally and secretly via organized and intelligent conspiracy by specialists such as medical personnel, maintenance companies, insurance planners, and insurance subscribers. In the case of car accidents, it is difficult to prove intentions; in particular, an insurance company with no investigation rights has practical limitations in proving the suspicions. This paper aims reveal that the detection of organized and conspired insurance fraud, which had previously been difficult, could be dramatically improved through conspiring insurance fraud detection modeling using social network analysis and visualization of the relation between suspected group entities and by seeking developmental research possibilities of data analysis techniques.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.2
• /
• pp.319-328
• /
• 2013

Considerable number of major countries have put great efforts to leverage the efficiency of power consumption using Smart Grid in order to resolve the critical issues with drastical growing demands regarding electricity, the crisis of environmental pollution and so on. There has been increasing number of researches to construct Smart Grid in Korea as well. The threats of cyber terror attacks which might cause national crisises in terms of economy and society have been climbing up because of the fact that Smart Grid employs bi-directional communications embedding the cyber threats from existing/legacy communication networks. Consequently, it is required to build concrete response processes including investigation and analysis on cyber breaches into Smart Grid. However, the digital evidence acquisition techniques do not suffice to be deployed in Smart Grid systems despite of the fact that the techniques, against cyber breaches into well-known networks, have been studied in plenty of time. This work proposes a novel digital evidence acquisition scheme appropriate to Smart Grid systems through intensive investigation of the evidence acquisition requirements in Smart Grid and the historical evidence acquisition methods.

• The Journal of the Korea Contents Association
• /
• v.20 no.9
• /
• pp.541-548
• /
• 2020

Interest in emotions continues to rise around the world, including Korea, and in recent years, new styles such as new-tro, a new term referring to 'gaem-seong' of the social networking service generation, have emerged. Considering the strong influence of emotion on time and the environment, it is necessary to recognize the public's emotion about the current new style. Thus, in this study, 12 emotional vocabulary words were selected from the nine products applied with the new-tro style: want, cute, happy, pleasure, unique, cool, stylish, pretty, fun, like, joy, and special. According to the analysis of the survey, men's emotions were higher in order of "funny-cute-happy," and women's emotions were higher in order of 40s, 30s, 50s and 20s. Emotional vocabulary extracted from this study can be used to evaluate the sensitivity of objects to which the new-tro style is applied and will be utilized as specific emotional evaluation data through the analysis methods presented.

• Journal of Agricultural Extension & Community Development
• /
• v.27 no.3
• /
• pp.125-134
• /
• 2020

The regional centrality plays a very important role in national and regional planning and it is measured by data such as people, goods, and information flows among regions. The inter-regional flows are usually considered by only direct flows, yet indirect flows, which are generated accordingly from direct flows, are not critically considered. Most centrality studies have also hardly reflected the indirect flow in the network analysis. This study demonstrates the significance of the indirect flows to enhance accuracy of the regional centrality. The nationwide dataset of inter-regional commuter traffic matrix is used in this study and analysed into two groups; one to consider only direct flow and the other both direct and indirect flows. The results indicate remarkable differences of centrality raking between two groups such as Yeongam of Jeonnam Province(+60th), Eumseong of Chungbuk Province(+57th), Gwacheon of Gyeonggi Province (-35th), and Nowon of Seoul (-32nd). It clearly shows the significant influence of indirect flow for regional centrality study. This also reveals regional centrality ranking in Korea by considering direct and indirect flows of commuters. Jung, Gangnam, and Jongno of Seoul are categorized in the highest rank group and Ulleung of Gyeongbuk, Ongjin of Incheon, and Jindo of Jeonnam are in the lowest group. The top group includes seven districts of Seoul, two of Busan, and one of Gyeonggi Province. The bottom group includes mostly island and costal areas. As this study shows an accurate method of centrality measurement, it has a significant implication to lead an effective regional planning.

• Journal of the Korean Geographical Society
• /
• v.32 no.2
• /
• pp.197-215
• /
• 1997

The purpose of this study is to show practices of teaching method based on the type of knowledge in geography education. The results of examining the type of knowledge according to the five themes in guidelines for geographic education in america are as follows: the empirical-analytic knowledge-centered contents are suited for designing concepts inquiry-centered teaching. The historical-hermeneutic knowledge-centered contents are suited for designing problem solving-centered teaching. The critical knowledge-centered contents are suited for designing decision-making-centered teaching. In this shsdy, 1 emphasized teaching method based on the type of knowledge in Ceographv Education according to the responses of students and academic achievement. However, in practice l propose that teachers construct their lesson plans according to their various spheres of interest.