• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5594-5615
• /
• 2019

Malicious social robots, which are disseminators of malicious information on social networks, seriously affect information security and network environments. The detection of malicious social robots is a hot topic and a significant concern for researchers. A method based on classification has been widely used for social robot detection. However, this method of classification is limited by an unbalanced data set in which legitimate, negative samples outnumber malicious robots (positive samples), which leads to unsatisfactory detection results. This paper proposes the use of generative adversarial networks (GANs) to extend the unbalanced data sets before training classifiers to improve the detection of social robots. Five popular oversampling algorithms were compared in the experiments, and the effects of imbalance degree and the expansion ratio of the original data on oversampling were studied. The experimental results showed that the proposed method achieved better detection performance compared with other algorithms in terms of the F1 measure. The GAN method also performed well when the imbalance degree was smaller than 15%.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.2
• /
• pp.111-120
• /
• 2016

Prior knowledge about the SNS (Social Network Services) datasets is often required to conduct valuable analysis using social media data. Understanding the characteristics of the information extracted from SNS datasets leaves much to be desired in many ways. This paper purposes on analyzing the detail of the target social network services, Twitter, Instagram, and YouTube to establish the spatial informatization process to integrate social media information with existing spatial datasets. In this study, valuable information in SNS datasets have been selected and total 12,938 data have been collected in Seoul via Open API. The dataset has been geo-coded and turned into the point form. We also removed the overlapped values of the dataset to conduct spatial integration with the existing building layers. The resultant of this spatial integration process will be utilized in various industries and become a fundamental resource to further studies related to geospatial integration using social media datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.5
• /
• pp.2194-2210
• /
• 2018

In the era of big data, consumers capture more and more economic surplus yet the seed of distrust also grows with the fast-spreading of social commerce, this paper began with the idea that product types may determine the degree of consumers' distrust even when identical discounts are offered for those products on Chinese social commerce websites. We also attempted to determine if distrust negatively affected consumers' purchase attitudes. 20 representative products that are commonly sold on social commerce websites in China were chosen to examine the relationships among product types, discount rates, distrust levels, and purchase attitudes. Inductive interview was used to collect the data as well as consumers' perceptions of the relationships. Data analysis results suggested that consumers like deep discounts, but their distrust levels increase along with the discount rates, however, the levels of increasing distrust vary according to product types. High, medium, and low discount rate categorizations were made and three propositions were suggested. This paper will contribute to the body of knowledge on online social commerce market and provide valuable implications for e-retailers and general consumers in online social commerce websites in China.

• Asia-Pacific Journal of Business
• /
• v.12 no.2
• /
• pp.161-174
• /
• 2021

Purpose - The purpose of this study was to examine the recent popular consumption trend, the hocance phenomenon, using social media big data. The study intended to present practical directions and marketing measures for the recovery and growth of the hotel industry after COVID-19 pandemic. Design/methodology/approach - Big data analysis has been used in various fields, and in this study, it was used to understand the hocance phenomenon. For three years from January 1, 2018 to December 31, 2020, we collected text data including the keyword 'hocance' from the blog and cafe of NAVER and Daum. TEXTOM and UCINET 6 were used to collect and analyze the data. Findings - According to the results of analysis, the words such as 'hocance', 'hotel', 'Seoul', 'travel', 'swimming pool', 'Incheon', 'breakfast', 'child' and 'friend' were identified with high frequency. The results of CONCOR analysis showed similar results in all three years. It has been confirmed that 'swimming pool', 'breakfast', 'child' and 'friend' are important when deciding on the hocance package. Research implications or Originality - The study was differentiated in that it used social media big data instead of traditional research methods. Furthermore, it reflected social phenomena as a consumption trend so there was practical value in establishing marketing strategies for the tourism and hotel industry.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.353-360
• /
• 2023

This paper explores notable shifts in the restaurant startup market following the lifting of social distancing measures. Key trends identified include an escalated interest in startups, a heightened focus on the quality and diversity of food, a relative decline in the importance of delivery services, and a growing interest in specific industry sectors. The study's data collection spanned three years, from April 2021 to May 2023, encompassing the period before and after social distancing. Data were sourced from a range of online platforms, including blogs, news sites, cafes, web documents, and intellectual forums, provided by Naver, Daum, and Google. From this collected data, the top 50 words were identified through a refinement process. The analysis was structured around the social distancing application period, comparing data from April 2021 to April 2022 with data from May 2022 to May 2023. These observed trend changes provide founders with valuable insights to seize new market opportunities and formulate effective startup strategies. In summary, We offer crucial insights for founders, enabling them to comprehend the evolving dynamics in food service startups and to adapt their strategies to the current market environment.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.8
• /
• pp.241-249
• /
• 2021

The aim of the research is to evaluate the impact of social media marketing (with special reference to Facebook) on the brand preference of customers with regard to smart mobile phones. Since Facebook has become very popular today and a trend has arisen to use social media as a marketing tool, the researcher intended to evaluate the impact of social media marketing on brand preference, as the findings would provide valuable insight for future businesses. Social media as measured social media visibility, social media engagement, and social media influencewas the independent variableand brand preference was the dependent variable. The convenience sampling method was used where the sample was taken from a group of people easy to contact or to reach. A sample of 186 young males and females was selected. Factor loading and factor analysis were used to analyze the data and find the most influencing factors on brand preference. Reliability analysis, validity analysis, and regression analysiswere performed to analyze the data. The R² value is 0.320 implying that 32.00% of the variance in brand preference is explained by social media influence, social media engagement, and social media visibility. The findings show thatsocial media visibility, social media engagement, and social media influencehave a positive impact on brand preference.

• Women's Health Nursing
• /
• v.17 no.2
• /
• pp.169-177
• /
• 2011

Purpose: This study was to compare social support and depression by gender, to investigate related factors, and to inquire effect of social support on depression by gender. Methods: This study analyzed raw data from a project funded by Jeju Province. The data were collected through home visit interview from 750 households which were selected by using randomized cluster sampling method. CES-D and MOS SSS were used for measuring depression and social support. Data obtained from 896 adults were analyzed using t-test, $x^2$ test and hierarchical regression. Results: There was no significant difference of depression prevalence, presenting 15.2% for men and 14.5% for women. The related factors were marital status, educational level, and socioeconomic status for men and only socioeconomic status for women. The result of hierarchical regression presented that social support was significant on depression, showing increase of $R^2$ from .151 to .328 when adding social support to other variables for men, increase of $R^2$ from .058 to .192 for women. Conclusion: The social support was an influential factor on depression both men and women, the development of strategies considering risk population by gender for enhancing social support to prevent and to manage depression was suggested.

• Journal of Korea Society of Industrial Information Systems
• /
• v.13 no.5
• /
• pp.133-141
• /
• 2008

Social Web is turning current Web into social platform for knowing people and sharing information. This paper takes major social tagging systems as examples, namely delicious, flickr and youtube, to analyze the social phenomena in the Social Web in order to identify the way of mediating and linking social data. A simple Tag Ontology (TO) is proposed to integrate different social tagging data and mediate and link with other related social metadata. Through several machine learning for tagging data, tag groups and similar user groups are extracted, and then used to learn the tagging ontology. A recommender system adopting the tag ontology is also suggested as an applying field.

• Research in Community and Public Health Nursing
• /
• v.29 no.2
• /
• pp.184-193
• /
• 2018

Purpose: The aim of this study is to examine a path model on the relationship among social capital, physical activity and subjective health status in the community indwelling elderly. Methods: The study was conducted utilizing the 2014 Seoul Survey, in the method of analyzing cross-sectional design and secondary data. Among 45,497 participants in total, the data of 4578 adults aged 65 or above was analyzed. Social capital was measured by social trust and social participation. Physical activity was measured by regular exercise. Additionally, a numerical rating scale was used to assess subjective health status. The data were analyzed using descriptive statistics, Pearson's correlation coefficients and path analysis. Results: Social participation and physical activity showed a direct effect on subjective health status in community indwelling elderly while social trust and physical activity showed an indirect effect on their subjective health status. The hypothetical path model of community indwelling elderly's subjective health status was proved correct. Conclusion: Findings from this study indicate that health-promoting intervention for community indwelling elderly should consider social trust and participation.

• Human Ecology Research
• /
• v.53 no.3
• /
• pp.293-307
• /
• 2015

Social commerce has a large impact on the emergence of the concept of society and individual lives that is recognized as one of the most important business areas in the Internet environment. A marketing agency, Trend Monitor (http://www.trendmonitor.co.kr), conducted a survey on social commerce usage and satisfaction level; subsequently, we used survey result data from 221 adult males and females for our research sample. Data analyses were conducted by reliability test, confirmatory factor analysis, t -test or one-way analysis of variance, and structural equation model (SEM) with IMB SPSS ver. 21.0 and ver. AMOS ver. 21.0. This study focused on multi-dimensional consumer innovativeness and found three elements of acceptability, competence, and distribution. Empirical verification through SEM presented data that suggests the three consumer innovativeness factors have a direct positive effect on social commerce that causes factors to indirectly affect satisfaction levels. This study indicated that the main consumption patterns in modern society take advantage of social commerce and satisfaction by improving a market economy to promote restoration. First, this study considers consumer innovativeness to have three factors. Secondly, research results help to understand relations between consumer innovativeness, use and satisfaction with social commerce that can help the social commerce industry establish effective market strategies through consumer innovativeness. The conclusion discusses implications for academic research and marketing strategies.