• Journal of Korea Trade
• /
• v.26 no.8
• /
• pp.37-57
• /
• 2022

Purpose -International diplomacy is key for the cohesive economic growth of countries around the world. This study aims to identify the major topics discussed and make sense of word pairs used in sentences by Chinese senior leaders during their diplomatic visits. It also compares the differences between key topics addressed during diplomatic visits to developed and developing countries. Design/methodology - We employed three methods: word frequency, co-word, and semantic network analysis. Text data are crawling state and official visit news released by the Ministry of Foreign Affairs of the People's Republic of China regarding diplomatic visits undertaken from 2015-2019. Findings - The results show economic and diplomatic relations most prominently during state and official visits. The discussion topics were classified according to nine centrality keywords most central to the structure and had the maximum influence in China. Moreover, the results showed that China's diplomatic issues and strategies differ between developed and developing countries. The topics mentioned in developing countries were more diverse. Originality/value - Our study proposes an effective approach to identify key topics in Chinese diplomatic talks with other countries. Moreover, it shows that discussion topics differ for developed and developing countries. The findings of this research can help researchers conduct empirical studies on diplomacy relationships and extend our method to other countries. Additionally, it can significantly help key policymakers gain insights into negotiations and establish a good diplomatic relationship with China.

• The Korean Journal of Applied Statistics
• /
• v.35 no.2
• /
• pp.189-201
• /
• 2022

In this study, we propose factor augmentation to improve forecasting power of cryptocurrency return. We consider financial and economic variables as well as psychological aspect for possible factors. To be more specific, financial and economic factors are obtained by applying principal factor analysis. Psychological factor is summarized by news sentiment analysis. We also visualize such factors through impulse response analysis. In the modeling perspective, we consider ARIMAX as the classical model, and random forest and deep learning to accommodate nonlinear features. As a result, we show that factor augmentation reduces prediction error and the GRU performed the best amongst all models considered.

• 한국노년학
• /
• v.41 no.3
• /
• pp.353-371
• /
• 2021

The purpose of this study is to provide clues to social welfare policy making by revealing discourse on social intervention and response based on big data on elderly living alone in the COVID-19 situation. Keyword analysis, network analysis, and topic analysis were utilized to explore the ways in which news media have portrayed challenges facing older individuals and the ways in which the central and local government as well as private organization have responded to them. Results are as follows. First, networks(degree, closeness, betweenness) were formed around region, delivery, society, support, and vulnerability, suggesting an increased demand for economic assistance and social support as well as stronger service delivery systems. Second, key topics derived included "establishing public delivery systems", "establishing local networks", "Managing care gap", "Establishing a private economic support system", and "Establishing service organization system". Based on the research results, discourse on the organic role of government, communities and the private sector has been presented, suggesting policy and practical implications by proposing a discussion on how to intervene for elderly living alone in disaster situations such as COVID-19.

• Journal of Platform Technology
• /
• v.11 no.3
• /
• pp.83-97
• /
• 2023

This research aims to identify startup trends by analyzing a large number of news articles through semantic network analysis. Using the BIGKinds article analysis service provided by the Korea Press Foundation, 330,628 news articles from 19 newspapers from January 2013 to December 2022 were comprehensively analyzed. The study focused on exploring the changes in key issues over the past decade, considering the impact of the social environment and global economic trends on entrepreneurship. We compared the number of news articles and changes in issues before and after the COVID-19 pandemic, and visualized entrepreneurship trends through frequency analysis, relationship analysis, and correlation analysis. The results of the study showed that the top keywords for entrepreneurship-related words are startup activation and commercialization, and the correlation between COVID-19 and entrepreneurship keywords is almost negligible in a linear sense, but the number of news articles decreased during the pandemic, which has an impact. In particular, the most frequently mentioned keywords are Ministry of SMEs and Startups, place is the United States, and person is limited. The agency was the SBA, and the entrepreneurship sector is more affected by social issues than any other sector, with the important characteristics of increased frequency of prompt access. This study supplies essential basic data for understanding and exploring issues and events related to entrepreneurship and suggests future research topics in the field.

• The Korean Journal of Applied Statistics
• /
• v.33 no.5
• /
• pp.639-653
• /
• 2020

Baker et al. (Quarterly Journal of Economics, 134, 1593-1636, 2016) developed an Economic Policy Uncertainty (EPU) index for South Korea in the same way as the U.S. EPU Index. However, the South Korean EPU index of Baker et al. (2016) has limitations as it did not fully reflect South Korean situation in terms of keyword selection and the selection of newspapers. We develop monthly South Korean economic policy uncertainty indexes with different keywords and news media. Various analyses have been conducted in order to examine the usefulness of the newly compiled indexes.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.1
• /
• pp.51-58
• /
• 2022

Various studies have been conducted from the past to the present because stock price forecasts provide stability in the national economy and huge profits to investors. Recently, there have been many studies that suggest stock price prediction models using various input data such as macroeconomic indicators and emotional analysis. However, since each study was conducted individually, it is difficult to objectively compare each method, and studies on their impact on stock price prediction are still insufficient. In this paper, the effect of input data currently mainly used on the stock price is evaluated through the predicted value of the deep learning model and the error rate of the actual stock price. In addition, unlike most papers in emotional analysis, emotional analysis using the news body was conducted, and a method of supplementing the results of each emotional analysis is proposed through three emotional analysis models. Through experiments predicting Microsoft's revised closing price, the results of emotional analysis were found to be the most important factor in stock price prediction. Especially, when all of input data is used, error rate of ensembled sentiment analysis model is reduced by 58% compared to the baseline.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.63-74
• /
• 2023

This study compared news coverage of national and international disasters, Hurricane Katrina and the Haiti Earthquake, using textual analysis of The New York Times and The Washington Post. The results reveal that media framing of the historical cases developed in three stages upon the development of post-disaster relief: (1) Call for humanitarian assistance; (2) New Orleans under anarchy and hopelessness vs. Haiti under scrutiny with hope; and (3) Katrina effects. By framing the outcomes of the hurricane as the "Katrina effect," the media used the disaster as a reference point to explain other economic and political issues. In addition, analysis of relevant statements and press releases confirmed that different social actors involved in the relief process, such as donors, facilitators, and beneficiaries, contributed to the media framing of the issue, although the facilitators were most successful in transferring their own frames to media frames. This study makes important contributions to the field as it looks beyond traditional relationships between quantitative measures of media attention and aid allocation. For governmental and nongovernmental organizations in the area of humanitarian assistance, the findings of this study will assist them in media-relations in the future.

• Journal of the Korean Society of Safety
• /
• v.33 no.2
• /
• pp.124-131
• /
• 2018

In consideration of limitations of the classic economic approach to risk evaluation and the psychometric analysis of risk perception, this study applies a facilitated modeling technique to a group of college students in Korea. In this group activities, researchers did not provide a pre-selected list of risk items. Instead, 35 participants had group discussions to generate 63 risk items, to rate their risk level and to evaluate their characteristics in terms of the level of knowledge and dreadfulness. This study also analyzes the influence of mass media, online news papers in particular, on risk perception by counting the number of news articles covering key word corresponding risk items generated. The results show that there are significant differences between the rank order of risk items generated by students and that of statistical or objective risk. Psychometric analyses find that the levels of knowledge and dreadfulness have meaningful correlations with risk level. A well known or a dreadful risk demonstrates a high level of risk. Correlation analyses of media coverage and the risk level also re-confirms strong positive relations. The larger number of news articles a risk issue was covered by, the higher level of risk it showed. It means that college students generated risk items on the basis of what they were exposed by media. The role of mass media in risk perception and the importance of risk communication in risk evaluation are underlined. Implications of research findings and future research are discussed as well.

• The Journal of the Korea Contents Association
• /
• v.16 no.5
• /
• pp.385-398
• /
• 2016

This research analyzed domestic newspapers' agenda setting trend and meaning construction process on the issue of marine environment by year. The research conducted a language network analysis and used R program and Netminer program to analyze four major daily newspapers' news coverages (Dong-A, Joongang, Hanhyoreh, and Kyunghyang) for the last ten years (2005-2014). The results show that the issue of marine environment in Korean media reports are signified in the economic context. For the last ten years, news reports are mainly focused on the 'development' issue of marine environment, without distinction of year. The core key words of the networks are "development", "plan", and "project." However, diverse strategies for 'preservation' are not covered in media reports as a major issue. The importance of effective preservation and reasonable development should be considered in a balanced way. Korean media coverages mainly concentrate on the development issue, and it has a strong influence on considering the marine environment area as an object of development. Future direction and implication of the press reports related to marine environment are discussed.

• Journal of Family Relations
• /
• v.22 no.4
• /
• pp.107-134
• /
• 2018

Objectives: The purpose of this study is to have diachronic understanding of holiday stress that has become the social issues through the analysis on the news articles about holiday stress from 1993 to 2016. Method: For this purpose, 416 articles and 457 cases about holiday stress from 5 daily newspapers such as Chosun Ilbo, Joongang Ilbo, Dong-A, Hankyoreh and Kyunghyang Shinmun etc. have been analyzed, conducting the qualitative and quantitative analysis together. Results: Firstly, the articles on holiday stress have been increased, showing the rapid increase per year for the last 20 years. It is presumed to be closely related to the socio-economic situation. Second, although there have been 'married women' overwhelmingly as the subject of holiday stress, the frequency of the young generation has been increasing recently including the 'married women'. Third, the 96.7% of the contents from psychological appeal appeared in the case of holiday stress is related to family values. Especially, the holiday stress related to 'value of patriarchy' was the biggest stress. However, there has been increasing holiday stress caused by 'value of kinship' and 'value of marriage' recently. Forth, as a countermeasure against the holiday stress, the 'perception on the change of family values' has been quantitatively suggested and it has become actively appeared in terms of contents after mid-2000s. However, it has been appeared low in terms of quantity and content recently. Conclusions: This study has significance since it has been verified that the holiday stress started from 'married women' but it has been expanded to the young generation and it is related to the change and co-existence of family values of our society.