• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.35-45
• /
• 2019

Recently, the damage with social cost of malicious comments is increasing. In addition to the news of talent committing suicide through the effects of malicious comments. The damage to malicious comments including abusive language and slang is increasing and spreading in various type and forms throughout society. In this paper, we propose a technique for detecting abusive language using a bi-directional long short-term memory neural network model. We collected comments on the web through the web crawler and processed the stopwords on unused words such as English Alphabet or special characters. For the stopwords processed comments, the bidirectional long short-term memory neural network model considering the front word and back word of sentences was used to determine and detect abusive language. In order to use the bi-directional long short-term memory neural network, the detected comments were subjected to morphological analysis and vectorization, and each word was labeled with abusive language. Experimental results showed a performance of 88.79% for a total of 9,288 comments screened and collected.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.1-7
• /
• 2019

With the in-depth development of machine learning, the deep learning method has made great progress, especially with the Convolution Neural Network(CNN). Compared with traditional text sentiment classification methods, deep learning based CNNs have made great progress in text classification and processing of complex multi-label and multi-classification experiments. However, there are also problems with the neural network for text sentiment classification. In this paper, we propose a fusion model based on Long-Short Term Memory networks(LSTM) and CNN deep learning methods, and applied to multi-category news datasets, and achieved good results. Experiments show that the fusion model based on deep learning has greatly improved the precision and accuracy of text sentiment classification. This method will become an important way to optimize the model and improve the performance of the model.

• Health Policy and Management
• /
• v.26 no.1
• /
• pp.51-62
• /
• 2016

Background: The publicness concept in healthcare has been built to its social consensus relying on historical context, with the result that the meaning of publicness has a great diversity and heterogeneous nature in Korea. Thus it needs to be addressed to clarify the meaning and boundary of the publicness concept in healthcare, so as to discuss its social implication. Methods: In order to investigate whether or how the publicness concept is used in healthcare, we conducted a text network analysis in 779 news articles from 8 Korean daily newspapers over a recent 5-year period. Results: The publicness concept was closely related to medicine and medical institution, and formed a conceptual network with public health, medicine, welfare, patient, government, Jin-ju city, and health. Keywords relating publicness tended to be similar between four major newspapers; however, the association with Jin-ju city, government, and society was noticeable in Kyunghyang Shinmun and Hankyoreh, and so was patient and service in Dong-A Ilbo. Conclusion: Publicness and medicine was closely associated, and government seemed to remain as a main actor for public interest. Publicness was related with a variety of actors and values, with its expanded boundary. The different contexts of publicness by newspapers might reflect each ideological inclination. The textual importance of publicness was relatively low in part, which suggests that publicness was used in a loose sense or as a routine.

• Journal of Internet Computing and Services
• /
• v.12 no.1
• /
• pp.39-53
• /
• 2011

Recently, a new media reform bill has passed through the National Assembly in Korea. The introduction of comprehensive programming channels that combine news and entertainment programs is expected to have a direct and indirect effect on the media related industry. And it affects not only existing traditional media operators, but also companies that consider entering the comprehensive programming business. This study analyzes the changes caused by the emergence of new businesses and identifies competitive strategies. Using Scenario Network Mapping (SNM) that is a scenario planning methodology for developing an industry network map in a complex environment. As a result of this study, the following competitive factors were identified: new business competitiveness, government policy and support, and content differentiation. This study has significance as an initial study on comprehensive programming channels strategies. It also provides implications to the government and the entrepreneur who is considering starting a comprehensive programming business.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.930-938
• /
• 2007

Captions which appear in images include information that relates to the images. In order to obtain the information carried by captions, the methods for text extraction from images have been developed. However, most existing methods can be applied to captions with fixed height of stroke's width. We propose a method which can be applied to various caption size. Our method is based on connected components. And then the edge pixels are detected and grouped into connected components. We analyze the properties of connected components and build a neural network which discriminates connected components which include captions from ones which do not. Experimental data is collected from broadcast programs such as news, documentaries, and show programs which include various height caption. Experimental result is evaluated by two criteria : recall and precision. Recall is the ratio of the identified captions in all the captions in images and the precision is the ratio of the captions in the objects identified as captions. The experiment shows that the proposed method can efficiently extract captions various in size.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.11
• /
• pp.143-150
• /
• 2015

Social network services can be defined as an individual web page which enables online, human-relationship building by collecting useful information and sharing it with specific or unspecific people. Recently, as the social network services(SNS) such as Twitter and Facebook have been paid attention in many fields of the society. SNSs are also one of the fastest channels to get news which people may not be able to see on TV or newspaper. The number of people who feel they are benefiting from social network services are increasing dramatically. A number of researches about SNS are underway. The study based on the Technology Acceptance Model empirically investigates the relationship between characteristics of SNS (system, service, information, and emotional) and user satisfaction of SNS. The study also analyzes how the relationshipa between SNS characteristics, satisfaction and user acceptance are moderated by country type of SNS users and inclination toward SNS acceptance. To achieve these research purposes, the study conducted various statistical analyses using questionnaire of the Korean and Chinese SNS users. The results of the study are followings. First, SNS characteristics have a positive effect to the user satisfaction. Second, SNS satisfaction have a positive effect to the user acceptance. Third, the relationship between SNS characteristics and user satisfaction is moderated by the country type of SNS users and inclination toward SNS acceptance. The study results could provide some implications to researchers who have interest in studying SNS, also could help business managers to operate and develop their SNS site more effectively.

• Database Research
• /
• v.34 no.3
• /
• pp.3-13
• /
• 2018

Text classification is one of the text mining technologies that classifies a given textual document into its appropriate categories and is used in various fields such as spam email detection, news classification, question answering, emotional analysis, and chat bot. In general, the text classification system utilizes machine learning algorithms, and among a number of algorithms, naïve Bayes and support vector machine, which are suitable for text data, are known to have reasonable performance. Recently, with the development of deep learning technology, several researches on applying deep neural networks such as recurrent neural networks (RNN) and convolutional neural networks (CNN) have been introduced to improve the performance of text classification system. However, the current text classification techniques have not yet reached the perfect level of text classification. This paper focuses on the fact that the text data is expressed as a vector only with the word dimensions, which impairs the semantic information inherent in the text, and proposes a neural network architecture based upon the semantic tensor space model.

• Smart Media Journal
• /
• v.11 no.8
• /
• pp.73-83
• /
• 2022

In order to support new construction engineering companies with weak information power to successfully advance into the overseas construction market, this study tried to analyze what are the keywords of interest in the overseas construction market and how they differ from Korea. For this purpose, we recently collected 2,473 news article titles and major articles targeting smart cities that are of high interest in Korea and Vietnam. Through network configuration and topic modeling, we examined the connection relationship between the word of interest and the word of interest. In addition, the influence of the word of interest in the network was measured using PageRank centrality. Through this analysis, it was found that there is a high interest in smart city-related construction, cities, and digital in both countries, and the difference in terms of interest between Korea and Vietnam was inferred. Finally, the limitations of this study and additional research directions to complement them are presented.

• Journal of Broadcast Engineering
• /
• v.23 no.4
• /
• pp.536-548
• /
• 2018

Public data has been transformed from provider-oriented information disclosure to a form of personalized information sharing centered on individual citizens since government 3.0. As a result, the government is implementing policies and projects to maximize the value of public data and increase reuse. This study analyzes the issues related to public data in the news and seeks the status of government agencies and government projects by issue. We conducted semantic analysis on domestic online news and public agency bidding information including public data and conducted the work of linking major key words derived with social and economic values inherent in public data. As a result, major issues related to public data were divided into broader access to public data, growth of new technology, cooperation and conflict among stakeholders, and utilization of the private sector, which were closely related to transparency, efficiency, participation, and innovation mechanisms. Also major agencies of four issues include the Ministry of Strategy and Finance and Seoul, Ministry of Culture, Sports and Tourism and Gyeonggi-do, Ministry of Trade, Industry and Energy and Incheon, and Ministry of Land, Infrastructure and Transport and Gyeongsangbuk-do. Most of the issues are being led by the government.

• Korean journal of communication and information
• /
• v.76
• /
• pp.151-182
• /
• 2016

The right to be forgotten (RTBF) has been a population notion to address privacy issues associated with the digitalization of information and the dissemination of such information over the global digital network. In May 2014, the European Court of Justice (ECJ) laid down a landmark RTBF decision to grant individuals the right to be de-listed from search results. ECJ's RTBF decision sparked an increased interest in RTBF in South Korea. Academic and non-academic commentators have provided a mistaken or outstretched interpretation of RTBF in claiming that removal of news articles should be read into RTBF in Korean law. Moreover, the Press Arbitration Commission of Korea (PAC) has proposed revising the Press Arbitration Act (PAA) to allow the alleged victims of news reporting to request the deletion of news stories. This article examines the notion of RTBF from its origin to the latest development abroad and also critically explores Korean laws regulation freedom of expression to evaluate if Korea needs the proposed PAA revision.