• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.4958-4970
• /
• 2019

As technology advances, the amount of fake news is increasing more and more by various reasons such as political issues and advertisement exaggeration. However, there have been very few research works on fake news detection, especially which uses grammatical transformation on deep neural network. In this paper, we shall present a new Fake News Detection Model, called FAGON(Fake news detection model using Grammatical transformation On deep Neural network) which determines efficiently if the proposition is true or not for the given article by learning grammatical transformation on neural network. Especially, our model focuses the Korean language. It consists of two modules: sentence generator and classification. The former generates multiple sentences which have the same meaning as the proposition, but with different grammar by training the grammatical transformation. The latter classifies the proposition as true or false by training with vectors generated from each sentence of the article and the multiple sentences obtained from the former model respectively. We shall show that our model is designed to detect fake news effectively by exploiting various grammatical transformation and proper classification structure.

• Journal of Fashion Business
• /
• v.22 no.2
• /
• pp.134-149
• /
• 2018

The number of children wearing make-up is increasing. "Children's cosmetics" is not a legal term though it is commonly used. The purpose of this study is to analyze discussions on children's cosmetics based on news articles found on the internet. This study also identifies what products are being distributed as children's cosmetics. Keyword searches were conducted using internet portal sites. Information was extracted from news articles and Best Item 100 for children's cosmetics. The results of analyzing news articles and Best Item 100 lists are as follows : 1. There were two main discussion topics in news articles. The first topic was related to marketing(the branding and trends of children's cosmetics). The other topic was about government regulations(side effects, harmful ingredients, control, regulations, attention, proper product usage, product categorization, and the overall safety of children's cosmetics). By 2014, many articles had covered government control and regulation. However, since 2017, news articles have focused on the product categorization and the concern for overall safety has dramatically increased. 2. Three different product categories have appeared in the Best Item 100; they are cosmetics, toys, and other products. In market, consumers recognized children's cosmetics as cosmetics and also as toys. Between 2017 and 2018's Best Item, other products are dramatically down, color cosmetics and single cosmetics are on the rise, and the purchase of domestic products has increased.

• Journal of Digital Convergence
• /
• v.11 no.7
• /
• pp.297-304
• /
• 2013

This research explores the effect of TV news camerawork and viewers' involvement on memory of news through experiment. For this experimental research, 2 groups of subjects composed of university students were exposed to different types of TV news and responded to survey questions which were analysed by SPSS program. This research found that camerawork of TV news doesn't have an effect on short-term memory but on long-term memory. Though the fact viewers' involvement has a positive effect on shot-term and long-term memory was found, interactive effect of viewers' involvement and camerawork as an peripheral clue was not found.

• Journal of the Korean Society for information Management
• /
• v.26 no.1
• /
• pp.305-320
• /
• 2009

The news pages provided through the web contain unnecessary information. This causes low performance and inefficiency of the news processing system. In this study, news content extraction methods, which are based on sentence identification and block-level tags news web pages, was suggested. To obtain optimal performance, combinations of these methods were applied. The results showed good performance when using an extraction method which applied the sentence identification and eliminated hyperlink text from web pages. Moreover, this method showed better results when combined with the extraction method which used block-level. Extraction methods, which used sentence identification, were effective for raising the extraction recall ratio.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.454-460
• /
• 2021

This study attempted to empirically analyze how the use of portal news is related with user's social credibility levels. 1100 subjects were sampled and online-surveyed. The amount of news usage and level of social credibility were measured respectively by the PNRBS(Portal News Readership Behavior Score) and SCI(Social Credibility Index) which were developed by the researcher. The results show that the relationship between scocial credibility and portal new use is not a linear but some V type. In terms of the mean score of social credibility index, non-portal news user is the highest while the light user is the lowest and the heavy user is the second highest.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.23-33
• /
• 2021

This study analyzed news articles about 'Young-Kl' reported by 11 media outlets, identifying news frames and quotation frames. Using a semantic network analysis, this study inspected the quotations frames and measured the frequency of the quotes and sources types. Also, the concentration index of the frames was measured. The results showed that news frames consisted of 10 topics and quotation frames consisted of 14 topics. Although the differences among quotation frames by media as well as by source types were observed, the concentration index of sources such as government, political arena, and business appeared high. Therefore, this study suggested that numerical diversity of news sources would not establish the diversity of news frames.

• The Journal of Information Systems
• /
• v.32 no.2
• /
• pp.87-108
• /
• 2023

Purpose The main purpose of this study is to improve fake news detection performance by using video information to overcome the limitations of extant text- and image-oriented studies that do not reflect the latest news consumption trend. Design/methodology/approach This study collected video clips and related information including news scripts, speakers' facial expression, and video metadata from YouTube to develop fake news detection model. Based on the collected data, seven combinations of related information (i.e. scripts, video metadata, facial expression, scripts and video metadata, scripts and facial expression, and scripts, video metadata, and facial expression) were used as an input for taining and evaluation. The input data was analyzed using six models such as support vector machine and deep neural network. The area under the curve(AUC) was used to evaluate the performance of classification model. Findings The results showed that the ACU and accuracy values of three features combination (scripts, video metadata, and facial expression) were the highest in logistic regression, naïve bayes, and deep neural network models. This result implied that the fake news detection could be improved by using video information(video metadata and facial expression). Sample size of this study was relatively small. The generalizablity of the results would be enhanced with a larger sample size.

• Bio news
• /
• no.3
• /
• pp.42-44
• /
• 2003

• Bio news
• /
• no.4
• /
• pp.48-51
• /
• 2003

• Venture DIGEST
• /
• s.137
• /
• pp.64-64
• /
• 2009