• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.78-79
• /
• 2018

최근 가짜뉴스가 무분별하게 확산되면서 가짜뉴스로 인한 경제적, 사회적 비용이 커지고 있다. 하루에 발생하는 가짜뉴스는 방대하며, 실제 뉴스기사를 악의적으로 재생산 또는 언론사를 사칭하는 방식으로 유포되고 있다. 이를 구분하기 위한 연구가 많으나, 공인된 뉴스 기사인지에 대한 신뢰성 입증과 관련된 연구 논문은 매우 적은 상황이다. 본 논문에서는 가짜뉴스 문제를 해결하기 위해 뉴스 플랫폼에 블록체인을 적용, 공인된 뉴스 제공자가 기사 내용에 대한 Fingerprint를 블록체인에 기록하여 공인된 기사 내용에 대한 신뢰성을 검증하는 방안에 대해 제안한다.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.294-302
• /
• 2022

Detection of fake news is a complex and a challenging task. Generation of fake news is very hard to stop, only steps to control its circulation may help in minimizing its impacts. Humans tend to believe in misleading false information. Researcher started with social media sites to categorize in terms of real or fake news. False information misleads any individual or an organization that may cause of big failure and any financial loss. Automatic system for detection of false information circulating on social media is an emerging area of research. It is gaining attention of both industry and academia since US presidential elections 2016. Fake news has negative and severe effects on individuals and organizations elongating its hostile effects on the society. Prediction of fake news in timely manner is important. This research focuses on detection of fake news spreaders. In this context, overall, 6 models are developed during this research, trained and tested with dataset of PAN 2020. Four approaches N-gram based; user statistics-based models are trained with different values of hyper parameters. Extensive grid search with cross validation is applied in each machine learning model. In N-gram based models, out of numerous machine learning models this research focused on better results yielding algorithms, assessed by deep reading of state-of-the-art related work in the field. For better accuracy, author aimed at developing models using Random Forest, Logistic Regression, SVM, and XGBoost. All four machine learning algorithms were trained with cross validated grid search hyper parameters. Advantages of this research over previous work is user statistics-based model and then ensemble learning model. Which were designed in a way to help classifying Twitter users as fake news spreader or not with highest reliability. User statistical model used 17 features, on the basis of which it categorized a Twitter user as malicious. New dataset based on predictions of machine learning models was constructed. And then Three techniques of simple mean, logistic regression and random forest in combination with ensemble model is applied. Logistic regression combined in ensemble model gave best training and testing results, achieving an accuracy of 72%.

• Journal of Korean Academy of Nursing
• /
• v.23 no.1
• /
• pp.16-28
• /
• 1993

The purpose of this study was to identify the im-. age of nursing, that is, to see how nursing is viewed in newspapers. Articles about nursing from two Korean daily newspapers from Jan. 1, 1987 to Dec.31, 1991 were examined for subject, type, attitude and author-ship. The inter-rater reliability was 0.89(by The Holsti method). The major findings were as follows : 1. The total number of articles were 110. 2. As for the subjests matter, articles related to professional nursing activities appeared most frequently(29.6%) , there about labor issues and activity to promote nurses's job climate 19.4%, and about official activities of nursing 11.2%. 3. Commentary articles appeared most frequently(41.2%) , Other article forms were straight news(27. 1％), contribution(17.6％) and inter-views (10.6%). 4. Feature stories acounted for 62.4% and news articles for 37.6%. Most of the articles were of national interests(96.5%), the rest(3.5%) of news from abroad. 5. Articles favorable toward nursing accounted for 54.1%, neutral 28.2%, negative 17.6%. 6. Many articles were written by the reporters (66.3%).

• The Journal of the Korea Contents Association
• /
• v.18 no.7
• /
• pp.609-619
• /
• 2018

Domestic broadcasting companies are obliged to provide the disaster information quickly to protect the public from the disaster, and people can prepare the disaster. Especially, Korea Broadcasting System (KBS) has a duty to deliver disaster news more quickly and accurately than other broadcasting companies because it is designated as a host broadcaster for disaster broadcasting services in accordance with Article 43 of the Broadcasting Act. This study examined how the KBS deals with social disaster news related to Zika virus, and evaluated whether they used the frames in a timely manner to help people prepare a disaster. Based on the results of this analysis, this study tried to suggest practical implications for measures to improve the efficiency and reliability of disaster news report.

• Journal of Applied Reliability
• /
• v.15 no.2
• /
• pp.108-123
• /
• 2015

Test and Evaluation (T&E) have been verifying the level of it's technological skill and the needed operational status of the development weapons. If the overall spectrum of test and evaluation is fulfilled substantially in the production & deployment, the needed level of the weapon system will be enhanced and also the reliability status will become higher considerably. We can know currently these issues through the mass media and all kinds of the news regarding the defense industry and programs. And so this article have studied the method of enhancing reliability of the test and evaluation, the 6 variables were selected through the discussion of the professional group. The the test and evaluation group needs consistently the professional training systems. After DT&E, we have to the event to verify the technical level of the development systems. We have to take the high level of the kinds of the environmental test. Scientific methods like system engineering will be adapted in process of the test and evaluation. The number of suitable test prototype in the test and evaluation is analysed more systematically. And we need to establish the standardization of the test and evaluation. If 6 variables are well analysed and adapted in the working field, the reliability of the test and evaluation will be considerably, the defense industry will take the chance to develope the future-oriented.

• Journal of Acupuncture Research
• /
• v.26 no.2
• /
• pp.189-199
• /
• 2009

Objectives : Despite the substantial amount of newspaper coverage related to complementary and alternative medicine on the internet in recent years, little is know about the quality of the health information. To evaluate health information of the newspaper articles on moxibustion available in Korea through Korean language search engines and Web sites. Methods : We searched 454 news stories about moxibustion between 1 January 2006 and 31 December 2008. Among them, 34 internet news coverage related to health information on moxibustion were selected and rated against eight categories by two individuals. Results : The inter-rater reliability of the two reviewers was assessed as 0.69, indicating a moderately high level of agreement. The overall rating score for 34 articles was 35.7${\pm}$17.2 for the statement criteria and 12.9${\pm}$17.0 for the satisfaction criteria. Overall, although they might be improving recently, the scores remain generally low. There was a statistically significant difference in the score of the newspaper coverage according to the type of evidence sources, including anecdotes. Conclusions : There is substantial variability in news reporting practices about moxibustion. It is urgently needed to enhance the information related to CAM including moxibustion through the news media in Korea.

• The Journal of Society for e-Business Studies
• /
• v.17 no.1
• /
• pp.173-187
• /
• 2012

As newspapers which have been major news media are being replaced by on-line news media in recent years, many researchers are paying attention to "comments(news users' short remarks on an article)", a newly emerged way of forming public opinion. This study is examining how the similarity between political disposition of on-line news visitors and that of news media impacts upon their evaluation on quality of comments from the viewpoint of 'social identity theory.' This study may have academic significance because it inspected the pattern of media usage and the cognition of comments in relation to political disposition for the first time and showed 'comments reading' and the function of comments to form public opinion(comments journalism).

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.51-59
• /
• 2024

This study examines the relationship between the release of the news and the individual stock returns. Investors utilize a variety of information sources to maximize stock returns when establishing investment strategies. News companies publish their articles based on stock recommendation reports of analysts, enhancing the reliability of the information. Defining release of a stock-recommendation news article as an event, we examine its economic impacts and propose a binary classification model that predicts the stock return 10 days after the event. XGBoost and LightGBM models are applied for the study with accuracy of 75%, 71% respectively. In addition, after categorizing the recommended stocks based on the listed market(KOSPI/KOSDAQ) and market capitalization(Big/Small), this study verifies difference in the accuracy of models across four sub-datasets. Finally, by conducting SHAP(Shapley Additive exPlanations) analysis, we identify the key variables in each model, reinforcing the interpretability of models.

• ETRI Journal
• /
• v.24 no.1
• /
• pp.1-11
• /
• 2002

A video summary abstracts the gist from an entire video and also enables efficient access to the desired content. In this paper, we propose a novel method for summarizing news video based on multimodal analysis of the content. The proposed method exploits the closed caption data to locate semantically meaningful highlights in a news video and speech signals in an audio stream to align the closed caption data with the video in a time-line. Then, the detected highlights are described using MPEG-7 Summarization Description Scheme, which allows efficient browsing of the content through such functionalities as multi-level abstracts and navigation guidance. Multimodal search and retrieval are also within the proposed framework. By indexing synchronized closed caption data, the video clips are searchable by inputting a text query. Intensive experiments with prototypical systems are presented to demonstrate the validity and reliability of the proposed method in real applications.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.8
• /
• pp.1133-1138
• /
• 2001

In this paper, we implemented that MMT(Multimedia Terminal) demonstrates spot news, weather forecast, sports news and cultural news employed CDMA mobile communication networks. The MMT displays mobile pictures/joint pictures/on screen ad and to make known Bus stop or Mobile stations. The MMT gives driver's and passenger's safety and valuable information for one's use GPS satellites. We verified to make real time mobile picture transfer use of CDMA2000 1×(IS-95C) network and development the scheduler control each module. This system tested on vehicle that train and bus. MMT was implemented high reliability and stability by the embedded system. The mobile terminal shows reliable data transfer rate about 74Kbps on IS-95C.