• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.7
• /
• pp.345-350
• /
• 2016

This research suggests the keyword filtering about disaster and the method of detecting area in real-time event detecting system by analyzing contents of twitter. The diffusion of smart-mobile has lead to a fast spread of SNS and nowadays, various researches based on studying SNS are being processed. Among SNS, the twitter has a characteristic of fast diffusion since it is written in 140 words of short paragraph. Therefore, the tweets that are written by twitter users are able to perform a role of sensor. By using these features the research has been constructed which detects the events that have been occurred. However, people became reluctant to open their information of location because it is reported that private information leakage are increasing. Also, problems associated with accuracy are occurred in process of analyzing the tweet contents that do not follow the spelling rule. Therefore, additional designing keyword filtering and the method of area detection on detecting real-time event process were required in order to develop the accuracy. This research suggests the method of keyword filtering about disaster and two methods of detecting area. One is the method of removing area noise which removes the noise that occurred in the local name words. And the other one is the method of determinating the area which confirms local name words by using landmarks. By applying the method of keyword filtering about disaster and two methods of detecting area, the accuracy has improved. It has improved 49% to 78% by using the method of removing area noise and the other accuracy has improved 49% to 89% by using the method of determinating the area.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.7
• /
• pp.297-306
• /
• 2019

This is a longitudinal study which aims to examine the effects of the use frequency of SNS on adolescents' stress and the relationship between the former and the latter, based on big five personality factors. To this end, the valid data of 994 adolescents were collected by administering questionnaires to the cohort groups of those using Facebook twice for one year(T1-T2). An analysis of the data showed that the use frequency of Facebook(T1) had no direct effects on stress(T2), and that there was an interaction between users' personality and the use frequency. In particular, users' stress(T2) was varied depending on neuroticism among personality factors, as the use frequency of Facebook(T1) increased. The higher the use frequency of Facebook, the more the stress in the group with weak neuroticism, while the higher the use frequency of Facebook, the less the stress in other group with strong neuroticism, probably because each group has different motivation for meeting their needs for social support: the former's stress may increase, since they has relatively lower needs for social support and face more conflicts as they more frequently use Facebook, while the latter's stress may decrease, because they have relatively stronger needs for social support and are likely to acquire psychological support, as they more frequently use it.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.7
• /
• pp.192-202
• /
• 2019

This study was a descriptive study to investigate the factors influencing on self-esteem, ego resilience, impulsivity and life stress on smartphone addiction among college students. The subjects include college students in some areas. Data was collected in November and December, 2018. Total 231 college students were analyzed in the study. Collected data was analyzed in frequency, percentage, and t-test to examine differences in smartphone addiction according to general characteristics. Pearson's correlation was performed to examine correlations between smartphone addiction and main variables, and the factors influencing smartphone addiction were analyzed in multiple regression. The findings show that genera, satisfaction with college life, hours of using a smartphone, hours of using SNS, ego resilience, impulsivity, and life stress had significant effects on smartphone addiction. The study examined relations between general characters and smartphone addiction and found that the level of smartphone addiction was high in female college students, those who were not satisfied with college life, and used a smartphone and SNS for many hours. Ego resilience had negative correlations with smartphone addiction, and impulsivity and life stress had positive correlations with it. Multi-variate regression analysis results show that gender, ego resilience, and life stress were factors that had important influences on the smartphone addiction of college students, having explanatory power of 35.6%. In short, colleges and universities need to develop a school-level program to improve the college life of students and reduce their stress to the minimum and create an environment of encouraging them to grow power of controlling their lives so that they can prevent smartphone addiction.

• The Journal of the Korea Contents Association
• /
• v.14 no.7
• /
• pp.395-406
• /
• 2014

This research observes how an adolescent's usage of social network services is related with media use time, and also tries to verify how a parent's participation in acting to limit usage time serves as a mediating effect. For this analysis, data from The Korean Information Society Development Institute [Korea Media Panel Research] was used, being a survey conducted on 1,572 students from primary to secondary and high schools nationwide. The subjects' gender in the final analysis was 818 male students and 754 female students. In addition, primary school students consisted of 672 individuals, 416 were from secondary and 484 from high schools. To verify the appropriateness of the model proposed in this research, analyzed through the structural equation, using social network services(SNS) was not shown to have an effect on media usage time. However, there was an indirect effect from the use of alternative activities. In addition, the parent's limitation of usage showed no effect on media use time. This research attempts to identify the reasons why parents' limiting the usage time, along with alternative activities, do not have any significant effect in reducing media usage time in this era of smart media evolution. Further, this research hopes to suggest meaningful and political implications for the nation and society to understand and resolve media addiction.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1595-1603
• /
• 2020

Online defamation incidents such as Internet news comments on portal sites, SNS, and community sites are increasing in recent years. Bias and hate expressions threaten online service users in various forms, such as invasion of privacy and personal attacks, and defamation issues. In the past few years, academia and industry have been approaching in various ways to solve this problem The purpose of this study is to build a dataset and experiment with deep learning classification modeling for detecting various bias expressions as well as hate expressions. The dataset was annotated 7 labels that 10 personnel cross-checked. In this study, each of the 7 classes in a dataset of about 137,111 Korean internet news comments is binary classified and analyzed through deep learning techniques. The Proposed technique used in this study is multi-channel CNN model with attention. As a result of the experiment, the weighted average f1 score was 70.32% of performance.

• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.1-17
• /
• 2015

In this paper, we report what we have observed with regards to a prediction model for the military based on enlisted men's internal(cumulative records) and external data(SNS data). This work is significant in the military's efforts to supervise them. In spite of their effort, many commanders have failed to prevent accidents by their subordinates. One of the important duties of officers' work is to take care of their subordinates in prevention unexpected accidents. However, it is hard to prevent accidents so we must attempt to determine a proper method. Our motivation for presenting this paper is to mate it possible to predict accidents using enlisted men's internal and external data. The biggest issue facing the military is the occurrence of accidents by enlisted men related to maladjustment and the relaxation of military discipline. The core method of preventing accidents by soldiers is to identify problems and manage them quickly. Commanders predict accidents by interviewing their soldiers and observing their surroundings. It requires considerable time and effort and results in a significant difference depending on the capabilities of the commanders. In this paper, we seek to predict accidents with objective data which can easily be obtained. Recently, records of enlisted men as well as SNS communication between commanders and soldiers, make it possible to predict and prevent accidents. This paper concerns the application of data mining to identify their interests, predict accidents and make use of internal and external data (SNS). We propose both a topic analysis and decision tree method. The study is conducted in two steps. First, topic analysis is conducted through the SNS of enlisted men. Second, the decision tree method is used to analyze the internal data with the results of the first analysis. The dependent variable for these analysis is the presence of any accidents. In order to analyze their SNS, we require tools such as text mining and topic analysis. We used SAS Enterprise Miner 12.1, which provides a text miner module. Our approach for finding their interests is composed of three main phases; collecting, topic analysis, and converting topic analysis results into points for using independent variables. In the first phase, we collect enlisted men's SNS data by commender's ID. After gathering unstructured SNS data, the topic analysis phase extracts issues from them. For simplicity, 5 topics(vacation, friends, stress, training, and sports) are extracted from 20,000 articles. In the third phase, using these 5 topics, we quantify them as personal points. After quantifying their topic, we include these results in independent variables which are composed of 15 internal data sets. Then, we make two decision trees. The first tree is composed of their internal data only. The second tree is composed of their external data(SNS) as well as their internal data. After that, we compare the results of misclassification from SAS E-miner. The first model's misclassification is 12.1%. On the other hand, second model's misclassification is 7.8%. This method predicts accidents with an accuracy of approximately 92%. The gap of the two models is 4.3%. Finally, we test if the difference between them is meaningful or not, using the McNemar test. The result of test is considered relevant.(p-value : 0.0003) This study has two limitations. First, the results of the experiments cannot be generalized, mainly because the experiment is limited to a small number of enlisted men's data. Additionally, various independent variables used in the decision tree model are used as categorical variables instead of continuous variables. So it suffers a loss of information. In spite of extensive efforts to provide prediction models for the military, commanders' predictions are accurate only when they have sufficient data about their subordinates. Our proposed methodology can provide support to decision-making in the military. This study is expected to contribute to the prevention of accidents in the military based on scientific analysis of enlisted men and proper management of them.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.16 no.2
• /
• pp.233-238
• /
• 2002

Moxibustion is one of major healing technique in oriental medicine. It has been widely used in many diseases such as rheumatoid arthritis, Hashimoto disease, breech presentation, etc. However, till now, effects of moxibustion on NK cell activity and relations between sympathetic nerve system(SNS) and the immune alteration induced by moxibustion were not well studied. This study was designed to evaluate effects of moxibustion on NK cell activity and the intervention of SNS in the alteration of NK cell activity induced by moxibustion. Splenic NK cytotoxity was measured in a standard 4-h 51Cr release assay. We measured the NK cytotoxity at after moxibustion stimulation for 1,3,5, and 7 days, and also measured the NK cell cytotoxity after 3 and 7 days burn stimulation with similar temperature. IL-2, IL-4, INF-γ in serum were measured by rat IL-2, IL-4, INF-γ ELISA TEST KIT. To evaluate the effects of sympathectomy on alteration of NK cell cytotoxity, 6-hydroxydopamine(6-OHDA : 5Omg/kg) was used. We showed that NK cell activity of moxibustion stimulation group increased at the 3rd day, and declined at 7th day in comparison with that of contol group. In moxibustion stimulation group, NK cell activity of 3 day stimulation group was significantly higher than sham group. On the contrary, in burn stimulation group, NK cell activity was significantly higher than that of sham groups at 3rd, 7th days. Patterns between moxibustion and burns were different. INF- γ level of 3 days moxibustion stimulation group significantly higher than sham group. IL 2 level among groups were not different. IL-4 was not detected in serum with this method. Sympathectomy abolished the NK cell activity alteration induced by moxibustion. The results suggest that moxibustion induces the alteration of NK cell activity, along with INF-γ and SNS is related to these effects.

• The Journal of the Korea Contents Association
• /
• v.15 no.7
• /
• pp.460-476
• /
• 2015

The purpose of this study is to provide practical implications on government crisis management strategies and on the use of SNS in crisis management. Specifically, this study analyzed Ministry of Drug and Food Safety's responses to paraben toothpaste issue, media coverage of paraben toothpaste issue, and public responses to paraben toothpaste issue. Through textual analysis and the network analysis of 45 news articles and 645 tweets, this study found that Ministry used one-way communication strategy and mostly negative issues regarding Ministry's crisis response strategies were diffused via the media and Twitter. This study was meaningful in that it highlighted the importance of media relations and use of SNS in crisis management. The findings of this study provide useful implications for government officials and PR practitioners in their crisis management and communication strategy.

• Journal of Distribution Science
• /
• v.10 no.3
• /
• pp.7-13
• /
• 2012

Recently, with the success of Groupon in the USA using the new business model referred to as social commerce, which is a commercial transaction involving group purchases on social network service (SNS), social commerce business receives much attention. Social commerce is capable of effectively promoting additional purchasing by customers through unprecedented price discounts and limiting the number of purchasers and time allotted for purchases, and is able to achieve promotional effects over and above those of simple product promotion due to customers' voluntary word of mouth. Although social commerce is effective for short-term increase in the sales of products, there are numerous dissenting opinions on whether it can promote repurchasing by customers. In particular, social commerce in Korea focuses only on unprecedented discounted prices and does not have the marketing effect that SNS can produce over and above the sales promotion. The objective of this study is to find the factors that influence the repurchase intention on social commerce and to analyze factors that contribute the social commerce product. For this, this study extracts repurchase intention factors and computes a repurchase probability to assess the influence of factors other than price discount on social commerce customers at the time of repurchasing. In addition, the importance of factors toward sales revenue for each of the social commerce products (e.g., restaurant/café, beauty, tour/leisure, show/exhibition, and fashion/clothes) is estimated by using the computed repurchase probabilities. The repurchase probability through the analysis can be used for development of social commerce business in Korea.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.42 no.3
• /
• pp.184-192
• /
• 2019

Focusing on the emerging influencer market of SNS (Social Network Service), This study attempts to clarify the priority of Influencer characteristics when the customer decided to purchase products through the promotion of influencers. Since the influencer marketing differs from the Online information source marketing, this study has an academic implication in that integrated the influence of the characteristics of the Online information sources and the characteristics of SNS contents. For this purpose, through the literature research on Information sources and Influencers, the characteristics of influencers were reconstructed and priorities were derived using the AHP (Analytic Hierarchy Process) technique. The upper layer of the AHP structure was set to expertise, trustworthiness, social attractiveness, and content attractiveness, and the lower layer structured the model with 13 subfactors. The results are summarized as follows. First, in the result of combining the importance of the $1^{st}$ and $2^{nd}$ classes, the detailed factors of expertise and trustworthiness, ranked from the top to six, are largely influenced in purchasing decisions in influencer marketing. Second, content attractiveness is the third rank in the $1^{st}$ layer. Influencer marketing shows that content is more important than social attractiveness. Besides, the $7^{th}$ to $9^{th}$ positions of the overall rankings accounted for visual information, storytelling, and external attractiveness, which are the details of content attractiveness, and it is confirmed that it is more effective for influencer marketing to emphasize content attractiveness than social attractiveness. Although the influencer marketing differs from the existing information marketing, this study has an academic implication in that integrated the influence of the characteristics of the source and the characteristics of the contents.