• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.6
• /
• pp.811-819
• /
• 2023

Understanding the local conditions is a crucial factor in enhancing the success potential of overseas construction projects. This can be achieved through the analysis of news articles of the target market using topic modeling techniques. In this study, the authors aimed to analyze news articles using two topic modeling methods, namely Latent Dirichlet Allocation (LDA) and BERTopic, in order to determine the optimal approach for market condition analysis. To evaluate the alignment between the generated topics and the actual themes of the news documents, the research collected 6,273 BBC news articles, created ground truth data for individual news article topics, and finally compared this ground truth with the results of the topic modeling. The F1 score for LDA was 0.011, while BERTopic achieved a score of 0.244. These results indicate that BERTopic more accurately reflected the actual topics of news articles, making it more effective for understanding the overseas construction market.

• Journal of Society of Preventive Korean Medicine
• /
• v.15 no.2
• /
• pp.131-143
• /
• 2011

Objective : The aims of this study are to investigate the trend of internet journalism about the toxicity and safety of the herbal medicine, and to suggest the regulatory solution of the issue. Method : In this study, we had searched the internet news article published from 2001 to 2011 in the five major portal sites-NAVER, DAUM, Nate, Google Korean, and Yahoo Korean. The search terms were 'herbal medicine', 'adverse event', 'toxicity'. If the articles described the same event in the same form and tone, the articles were considered overlapping. The overlapped articles were excluded. The articles were categorized by the form and tone. The form categories were straight news, interpretative story, editorial, interview, and the tone categories are the positive, the negative, and the neutral. The regulations were searched about the negative issue. Result : Total 56 articles were reviewed. There were 19 positive articles, 29 negative articles, 8 neutral articles. Most negative issues have the proper regulations, but insufficient measures for the adverse event reporting system. Conclusion : The herbal medicine specified adverse event reporting system is essential.

• Journal of Preventive Medicine and Public Health
• /
• v.53 no.2
• /
• pp.126-134
• /
• 2020

Objectives: Cancer diagnoses have a tremendous impact on individuals and communities, drawing intense public concern. The objective of the current research was to examine news coverage and content related to cancer-related issues in Korean newspapers. Methods: Primarily using the database system of the Korea Press Foundation, we conducted a content analysis of 2806 articles from 9 Korean daily newspapers during a recent 3-year period from 2015 to 2017. Thematic categories, the types of articles, attitudes and tone, and the number of sources in each article were coded and classified. Results: Many news articles dealt with a diverse range of themes related to cancer, including general healthcare information, the latest research and development, specific medical institutions and personnel, and technology and products, which jointly accounted for 74.8% of all articles. Those thematic categories differed markedly in terms of article type, tone, and the number of cited sources. News articles provided extensive information about healthcare resources, and many articles seemed to contain advertising content. However, the content related to complex social issues such as National Health Insurance did not include enough information for the reader to contextualize the issues properly or present the issues systematically. Conclusions: It can be assumed that the media exert differential influence on individuals through news coverage. Within the present reporting framework, the availability and usefulness of information are likely to depend solely on individuals' capabilities, such as financial and health literacy; this dependency has a negative impact on knowledge gaps and health inequities.

• Journal of Internet Computing and Services
• /
• v.14 no.6
• /
• pp.85-94
• /
• 2013

With the emergence of world wide web, in particular web 2.0 the rapidly growing amount of news articles has created a problem for users in selection of news articles according to their requirements. To overcome this problem different clustering mechanism has been proposed to broadly categorize news articles. However these techniques are totally machine oriented techniques and lack users' participation in the process of decision making for membership of clustering. In order to overcome the issue of zero-participation in the process of clustering news articles in this paper we have proposed a framework for clustering news articles by combining users' judgments that they post on twitter with the news articles to cluster the objects. We have employed twitter hash-tags for this purpose. Furthermore we have computed the credibility of users' based on frequency of retweets for their tweets in order to enhance the accuracy of the clustering membership function. In order to test performance of proposed methodology, we performed experiments on tweets messages tweeted during general election 2013 in Pakistan. Our results proved over claim that using users' output better outcome can be achieved then ordinary clustering algorithms.

• Journal of the Korean Society for Library and Information Science
• /
• v.58 no.3
• /
• pp.65-89
• /
• 2024

This study developed a model to classify news articles into categories of topic, genre, and region using a Korean Pre-trained Language model. To achieve this, a new news article classification system was designed by referring to the classification systems of domestic media outlets. The topic and genre classification models were implemented as hierarchical classification models that link the main categories and subcategories, and their performance was compared with that of an integrated category model. The evaluation results showed that the hierarchical structure classification model had the advantage of providing more precise categorization in ambiguous or overlapping categories compared to the integrated category model. For regional classification of news articles, a model was built to classify into 18 categories, and for regional news articles, the regional characteristics were clearly reflected in the text, resulting in high performance. This study demonstrated the effectiveness of classifying news articles from multiple perspectives-topic, genre, and region-and emphasized the significance of suggesting the potential for a multi-dimensional news article classification service that meets user needs.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.8
• /
• pp.251-258
• /
• 2020

A training dataset for text summarization consists of pairs of a document and its summary. As conventional approaches to building text summarization dataset are human labor intensive, it is not easy to construct large datasets for text summarization. A collection of news articles is one of the most popular resources for text summarization because it is easily accessible, large-scale and high-quality text. From social media news services, we can collect not only headlines and subheads of news articles but also summary descriptions that human editors write about the news articles. Approximately 425,000 pairs of news articles and their summaries are collected from social media. We implemented an automatic extractive summarizer and trained it on the dataset. The performance of the summarizer is compared with unsupervised models. The summarizer achieved better results than unsupervised models in terms of ROUGE score.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.111-119
• /
• 2023

This study aimed to analyze the changes in news articles related to 'Elderly Living Alone' by comparing Big Data-based news articles related to 'Elderly Living Alone' reported before and after the outbreak of COVID-19. For this, 2018 to 2019 were selected before the outbreak of COVID-19, and 2020 to 2021 were selected after the outbreak, and news articles related to 'Elderly Living Alone' were collected and analyzed using BIGKinds. The main results are as follows. First, the number of related articles decreased after the outbreak of COVID-19 compared to before. Second, there was no significant difference in the analysis of related words. Third, in the relationship diagram analysis, 'Executives' before the outbreak of COVID-19 and 'Corona 19' after that showed the most weight. This study is expected to be used as basic data in preparing improvement plans for national policies and systems in the context of the spread of infectious diseases in relation to 'Elderly Living Alone'.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.89-91
• /
• 2017

A currency exchange is the rate to exchange currencies between different countries and the one of important factors to measure the economic size or status of a country. The currency exchange is affected by various economic or social events and changed dynamically. However, since too many economic and social factors affect the exchange rate and the leverage rate of each factor is so floating, it is difficult to define clearly the relationships between the exchange rate and the specific factor. In this paper, we analyze the data pattern for the exchange rate and news articles. To do this, we counts the frequencies of words presented in the news articles during specific periods and compare the frequencies with the margins of exchange rates.

• Korean journal of communication and information
• /
• v.23
• /
• pp.153-187
• /
• 2003

The main purpose of this study was to examine the characteristics of corporate PR practitioners whose opinions were quoted as news sources and of the related articles in the economic section of the nation's three largest newspapers. The results revealed that the PR practitioners were mostly males with the job title of general manager or manager working for large electronics/IT or financing companies in Seoul and near metropolitan areas. In particular, such overwhelming features were more clearly salient in the articles related to conflicts. However, the phenomena seem to have been somewhat eased since 2002 when the newspapers came out with the specialized economic section. Analyzing the articles in terms of the channel of covering news, theme of news, and the existence of any conflict, we found statistically significant differences in the characteristics of PR practitioners. In addition, the comparison between each period before and after the emergence of the specialized economic section also showed statistically significant differences in the characteristics of the PR practitioners in many cases.

• Knowledge Management Research
• /
• v.14 no.4
• /
• pp.1-17
• /
• 2013

As online communities proliferate, online news sites have received great attention in news media research. Although most of the online news sites provide contents for free, some have adopted the Pay-What-You-Want (PWYW) model by offering a voluntary payment option to the readers. In this study, we investigate the factors which influence subscribers' voluntary payment behavior on an online news site. Drawing upon both the Stimulus-Organism-Response (SOR) framework and the Elaboration Likelihood Model (ELM), we hypothesize that appreciation has a direct effect on the subscribers' voluntary payment behavior, whereas central factors (positive emotional content, cognitive content) and peripheral factors (news sharing, news article length) of the news articles have indirect impacts on voluntary payment behavior through the enhanced appreciation. Based on an empirical analysis of 172 news articles from the Korean online news site that adopted the PWYW pricing model (i.e., Ohmynews.com), we find that appreciation plays a critical role in voluntary payment behavior and that peripheral factors have significant impacts on appreciation. However, the impacts of central factors on appreciation are not found. By identifying influencing factors of subscribers' voluntary payment behavior on online news sites for the first time, this paper suggests a prospective alternative profit model for online news providers faced with fierce competition.