• Journal of the Korea Society of Computer and Information
• /
• v.23 no.1
• /
• pp.9-15
• /
• 2018

Policy polls, which investigate the degree of support that the policy has for policy implementation, play an important role in making decisions. As the number of Internet users increases, the public is actively commenting on their policy news stories. Current policy polls tend to rely heavily on phone and offline surveys. Collecting and analyzing policy articles is useful in policy surveys. In this study, we propose a method of analyzing comments using deep learning technology showing outstanding performance in various fields. In particular, we designed various models based on the recurrent neural network (RNN) which is suitable for sequential data and compared the performance with the support vector machine (SVM), which is a traditional machine learning model. For all test sets, the SVM model show an accuracy of 0.73 and the RNN model have an accuracy of 0.83.

• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.250-259
• /
• 2019

Big data processing technology and artificial intelligence (AI) are increasingly attracting attention. Natural language processing is an important research area of artificial intelligence. In this paper, we use Korean news articles to extract topic distributions in documents and word distribution vectors in topics through LDA-based Topic Modeling. Then, we use Word2vec to vector words, and generate a weight matrix to derive the relevance SCORE considering the semantic relationship between the words. We propose a way to recommend documents in order of high score.

• Journal of Multimedia Information System
• /
• v.8 no.4
• /
• pp.285-294
• /
• 2021

The development process of domestic CG (Computer Graphics) needs to be studied by classifying the technical part and the design part. This paper analyzes how early domestic broadcast equipment evolved and focused on what went through the development process. Domestic broadcasting companies have introduced and used overseas equipment and have begun to develop their own technology. The development process of the early domestic production technology of broadcasting stations was classified into Character Generator, On-line Real-Time Graphic and Sport Coder. It was found that the orientation of broadcasting technology was conclusively focused on visualization, with socio-cultural factors acting along with the evolution of hardware and software. This research is meaningful in reorganizing the history of the development process of domestic CG technology in the early days through previous research (primary verification), newspaper articles and news coverage (secondary verification). This paper looks at what is missing by regaining the past of CG, and argues that with the advent of new technologies today, we must develop through appropriate division of roles and collaboration between engineers and designers.

• Journal of The Korean Association For Science Education
• /
• v.41 no.1
• /
• pp.59-70
• /
• 2021

Ability to make informed decisions by critically evaluating media information on socioscientific issues (SSI) is one of the crucial elements of scientific literacy that citizens should obtain. This study aims to investigate how middle school students evaluated media information about socioscientific issues (SSI) when they faced two different types of information (i.e., numerical and empathic information). To achieve the aim, 96 middle school students responded to the questionnaires asking them to evaluate reliability and persuasiveness of SSI media information. The questionnaires consisted of two sets of newspaper articles on each SSI (pro-numerical/empathic, against-numerical/empathic). After reading the articles, the students evaluated reliability and persuasiveness of each article and wrote the reasons for their evaluation. The results were as follows: First, the students believed that news articles with numerical information were more reliable than the ones with empathic information in all SSI contexts. They tended to trust scientific evidence and data from numerical information, and real cases, societal problems, expressions, and values from empathic information. In addition, they evaluated their reliability based on the logic of information, accuracy of information, breadth and depth of data, and quantity and quality of sources both numerical and empathic information. Second, in case of evaluating persuasiveness of the articles, they focused more on the values that information contained, richness and logicality of the information, rather than the types of information, regardless of the type of information.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.4
• /
• pp.595-599
• /
• 2018

Sufficient understanding of oversea construction market status is crucial to get profitability in the international construction project. Plenty of researchers have been considering the news article as a fine data source for figuring out the market condition, since the data includes market information such as political, economic, and social issue. Since the text data exists in unstructured format with huge size, various text-mining techniques were studied to reduce the unnecessary manpower, time, and cost to summarize the data. However, there are some limitations to extract the needed information from the news article because of the existence of various topics in the data. This research is aimed to overcome the problems and contribute to summarization of market status by performing topic modeling with Latent Dirichlet Allocation. With assuming that 10 topics existed in the corpus, the topics included projects for user convenience (topic-2), private supports to solve poverty problems in Africa (topic-4), and so on. By grouping the topics in the news articles, the results could improve extracting useful information and summarizing the market status.

• Acta Via Serica
• /
• v.3 no.2
• /
• pp.181-196
• /
• 2018

In Turkey, academic studies on Korea are mostly focused on the Korean war and Korean language and literature. Conversely, in Korea, it seems that academic studies are largely focused on old Turkic history and Turkish language and literature. Unfortunately, on both sides, there is not a satisfiying number of studies on the Turkic diaspora in Korea. However, it is a reality that there was a Turco-Tatar group that lived in Korea at the time of the Japanese occupation between the two world wars. This group became Turkish subjects after World War II and became a bridge between Korea and Turkey. After the Russian revolution, around 1919, some Turco-Tatar groups like the Bashkir and the Misher emigrated to East Asia like the Manchuria region of China and Korea. Beginning from the 1920s, some families moved to Japan, but a group of Turco-Tatar stayed in Korean cities like Seoul (Keijo), Pusan and Daegu. The Turco-Tatar groups of East Asia established schools and mosques in Seoul, Korea; Harbin, Manchuria; Kobe, Nagoya; and Tokyo in Japan. A Moslem printing house (Matbaa-i ${\dot{I}}slamiye$) was also established in Tokyo in the 1930s. Many books, a newspaper and a magazine were published by this printing house. The name of the magazine was Yanga Yapon Muhbiri(New Japanese Courier), and it survived between 1931 and 1938. In this magazine, there were many interesting news and data about Korea and the Turco-Tatars of Korea. In this short article, we will try to bring out the importance of this magazine by giving samples of the articles which were written on the Turco-Tatar diaspora in Korea.

• Journal of the Korean Society for Library and Information Science
• /
• v.55 no.2
• /
• pp.91-110
• /
• 2021

In the face of the prolonged Covid-19, this study conducted a network analysis to propose the policy direction for the Korean National Assembly to go forward. Using COVID-19 news articles, various types of networks were created and analyzed for the parliamentary activities of the Korean National Assembly related to Covid-19. Specifically, we utilize the co-occurrence and keyword information to generate two types of parliamentary networks: co-occurrence-based network and content-based network. In addition, a topic keyword-driven parliamentary network was constructed by using topic modeling. The results of the study are as follows. First, lawmakers in the ruling party had a wide range of topics regarding Covid-19, while lawmakers from other political parties had a limited number of issues covered. Next, a few representative legislators were identified as influential actors in most of the centrality indicators. Based on the research results, cooperation on diverse agendas related to Covid-19 should be promoted between lawmakers from various political parties. And representative legislators from both major parties should play a crucial role as intermediaries to increase communication between them.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.5 no.3 s.18
• /
• pp.1-9
• /
• 2005

The primary source of disaster information for victims as well as ordinary people is mass media. In spite of their importance, the media often inaccurately portrays reality, which has stimulated academic debates. In Korea, however, media reporting patters of disaster have been hardly addressed. Therefore, the paper analyzes how newspaper and television news have reported typhoon Rusa between August 29 and October 1 in 2002 by using KINDS(Korean Integrated News Database System). The results show that television news tend to present more soft news stories emphasizing human interest stories than newspaper articles, relying on victims as primary interviewees. It is also pointed out that the Korean media do not play a significant role in providing disaster information to public regarding how to lessen the effects of impact through preparation. Disaster mythology representing wrong beliefs about human behavior in disaster is found in Korean media reporting, too. Unlike their western counterparts, however, Korean media seem to use the dependency image of helpless victims in order to stimulate donations. Analyses of disaster reporting patterns suggest that, in make disaster warning messages associated with behavioral responses, credible and official sources should provide clear and precise warning messages to the media, and the media also need to stress individual responsibilities in protecting his or her own properties not to make victims heavily dependent on public supports, while inducing donations.

• The Journal of the Korea Contents Association
• /
• v.16 no.8
• /
• pp.180-191
• /
• 2016

This study utilized a semantic network analysis for Korean major newspaper articles concerning 'Bernie Sanders'. 'Bernie Sanders' promotes conservative values of 'Americana' as well as the progressive values of 'relieving inequality', and thus, perhaps he is a subject on which ideological differences between the press can be distinctively manifest. Upon comparison of the priority of frequency between the conservative press and progressive press, the conservative press frequently used the expressions, 'socialist' and 'black man', whereas the progressive press frequently used the expressions, 'inequality' and 'problem'. Both the conservative press and progressive press displayed particularly different semantic compositions with the term, 'Korea'. The progressive press aimed to express the criticism of social problems and established politics identified by Sanders in relation to the 'Korean' society, whereas the conservative press criticized the blunt expressions stating that a specifically named politician resembles Sanders, and the specific party and term of 'Korea'. A completely different disposition of reports from different perspectives and context was ascertained, regardless of the use of the same terms. Thus, it is demonstrated that the semantic composition of the press on a specific issue displays significant differences according to their ideological disposition.

• Korean journal of communication and information
• /
• v.50
• /
• pp.164-186
• /
• 2010

Korean society, suffered from a severe currency crisis in 1997, had scarcely missed another market meltdown in 2008. However, neither economic fundamentals nor has political stability little to do with the recent crises. This paper thus projects the possibility of 'self-fulfilling crisis' in which the media took a critical part in amplifying 'crisis discourses.' For the purpose of understanding of media's impact on such a crisis, at first, this paper chose 'September Crisis in 2008' as a case study. While collecting news articles about the crisis, then, total 118 news articles collected from mainstream newspapers such as DongA-ilbo and Money Today have been analyzed in terms of media frame and discourse strategies. Research results showed that not only has the crisis discourse been shifted by economic situations, but the media re-constructed economic realities in way of justifying their political ideology and loyal readership. Taking those findings into consideration, in final, the authors urged the media to improve their performance by embracing more responsible and professional manners.