• Journal of the Korean Society for information Management
• /
• v.39 no.2
• /
• pp.275-298
• /
• 2022

This study examined the issues and characteristics that appeared in news and journal articles related to the 'right to be forgotten' using text mining analysis. Data for analysis were collected from 2010 to 2020 with the keyword 'right to be forgotten'. Keyword analysis and topic modeling analysis were performed on the collected data. As a result, in the last 10 years the issues about 'right to be forgotten' are not much different in news and journal articles and the approaches also are similar. However, it confirmed common issues and the partial difference between news and journal articles through comparison. Therefore in Archives and Records Management Studies, it is necessary to discuss derived in this study. In particular common issues are considered first but if there are differences in issues, it is needed to discuss them in various ways. This study is meaningful to understand the meaning and to draw issues that may arise in the future of the 'right to be forgotten'. The results of this study will contribute to be variously discussed on the 'right to be forgotten' in Archives and Records Management Studies.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.5
• /
• pp.129-153
• /
• 2023

This study was conducted in the context of the Covid-19 pandemic by analyzing a large amount of press report frames regarding the Covid-19 vaccine which is of great public interest, in order to explore the role and direction of trusted media as core elements of crisis communication. The study period lasted for eight months beginning in November 2020 when the development of the Covid-19 vaccine was in progress until June 2021. Set-up as research subjects were the Chosun Ilbo, Joongang Ilbo, Dong-A Ilbo and Hankyoreh according to their public confidence rankings and number of readers.The analysis method used structured topic Modeling (STM) and semantic network analysis. As a result, based on a clear cluster of word structures and a central analysis value, a total of 64 relevant frames, 16 for each news company, were gathered. In the third phase a comparative analysis of the four news companies was carried out to verify the organizational degree of the frames and substantial differences.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.579-585
• /
• 2023

The purpose of this study is to explore keywords within stalking-related news articles according to political orientation through the text network analysis, and then to examine the implicit intentions. Selecting total 1,607 articles including 824 articles of the conservative press(The Chosun Ilbo, The Joongang Ilbo) and 783 articles of the progressive press(The Hankyoreh, The Kyunghyang Shinmun) reported from January 1, 2018 to December 31, 2022, this study explored the aspect of topic category drawn through the topic modeling technique based on LDA(Latent Dirichlet Allocation). In the results of this study, the common topics of the conservative and progressive press were improvement of the perception of gender-based violence, personal protection & intensity of punishment, and disclosure of stalkers' personal information. Regarding the topics differently shown in those two press, the conservative press showed stalkers' harmful act, and outline of 'murder case at Sindang Station' while the progressive press showed request for aggravated punishment on the 'murder case at Sindang Station', and eradication of sexual exploitation crime (in cyber space). The results of this study imply that there are changes in the type of reporting according to ideological opinions about stalking in news articles.

• Communications for Statistical Applications and Methods
• /
• v.19 no.6
• /
• pp.771-780
• /
• 2012

In the current analysis, we examine news coverage data widely used in media studies. News coverage data is usually time series data to capture the volume or the tone of the news media's coverage of a topic. We first describe the distributional properties of autoregressive conditionally heteroscadestic(ARCH) effects and compare two major American newspaper's coverage of U.S.-North Korea relations. Subsequently, we propose a change point detection model and apply it to the detection of major change points in the tone of American newspaper coverage of U.S.-North Korea relations.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.57-71
• /
• 2013

Over a billion people in the world generate new news minute by minute. People forecasts some news but most news are from unexpected events such as natural disasters, accidents, crimes. People spend much time to watch a huge amount of news delivered from many media because they want to understand what is happening now, to predict what might happen in the near future, and to share and discuss on the news. People make better daily decisions through watching and obtaining useful information from news they saw. However, it is difficult that people choose news suitable to them and obtain useful information from the news because there are so many news media such as portal sites, broadcasters, and most news articles consist of gossipy news and breaking news. User interest changes over time and many people have no interest in outdated news. From this fact, applying users' recent interest to personalized news service is also required in news service. It means that personalized news service should dynamically manage user profiles. In this paper, a content-based news recommendation system is proposed to provide the personalized news service. For a personalized service, user's personal information is requisitely required. Social network service is used to extract user information for personalization service. The proposed system constructs dynamic user profile based on recent user information of Facebook, which is one of social network services. User information contains personal information, recent articles, and Facebook Page information. Facebook Pages are used for businesses, organizations and brands to share their contents and connect with people. Facebook users can add Facebook Page to specify their interest in the Page. The proposed system uses this Page information to create user profile, and to match user preferences to news topics. However, some Pages are not directly matched to news topic because Page deals with individual objects and do not provide topic information suitable to news. Freebase, which is a large collaborative database of well-known people, places, things, is used to match Page to news topic by using hierarchy information of its objects. By using recent Page information and articles of Facebook users, the proposed systems can own dynamic user profile. The generated user profile is used to measure user preferences on news. To generate news profile, news category predefined by news media is used and keywords of news articles are extracted after analysis of news contents including title, category, and scripts. TF-IDF technique, which reflects how important a word is to a document in a corpus, is used to identify keywords of each news article. For user profile and news profile, same format is used to efficiently measure similarity between user preferences and news. The proposed system calculates all similarity values between user profiles and news profiles. Existing methods of similarity calculation in vector space model do not cover synonym, hypernym and hyponym because they only handle given words in vector space model. The proposed system applies WordNet to similarity calculation to overcome the limitation. Top-N news articles, which have high similarity value for a target user, are recommended to the user. To evaluate the proposed news recommendation system, user profiles are generated using Facebook account with participants consent, and we implement a Web crawler to extract news information from PBS, which is non-profit public broadcasting television network in the United States, and construct news profiles. We compare the performance of the proposed method with that of benchmark algorithms. One is a traditional method based on TF-IDF. Another is 6Sub-Vectors method that divides the points to get keywords into six parts. Experimental results demonstrate that the proposed system provide useful news to users by applying user's social network information and WordNet functions, in terms of prediction error of recommended news.

• The Journal of the Korea Contents Association
• /
• v.20 no.7
• /
• pp.66-85
• /
• 2020

The purpose of this study is to explain and predict trends the AI development process based on AI technology patents (total) and AI reporting frames in major newspapers. To that end, a summary of South Korean and U.S. technology patents filed over the past nine years and the AI (Artificial Intelligence) news text of major domestic newspapers were analyzed. In this study, Topic Modeling and Time Series Return Analysis using Big Data were used, and additional network agenda correlation and regression analysis techniques were used. First, the results of this study were confirmed in the order of artificial intelligence and algorithm 5G (hot AI technology) in the AI technical patent summary, and in the news report, AI industrial application and data analysis market application were confirmed in the order, indicating the trend of reporting on AI's social culture. Second, as a result of the time series regression analysis, the social and cultural use of AI and the start of industrial application were derived from the rising trend topics. The downward trend was centered on system and hardware technology. Third, QAP analysis using correlation and regression relationship showed a high correlation between AI technology patents and news reporting frames. Through this, AI technology patents and news reporting frames have tended to be socially constructed by the determinants of media discourse in AI development.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.39-46
• /
• 2021

This study is about a method of extracting a summary from a news article in consideration of the importance of each sentence constituting the article. We propose a method of calculating sentence importance by extracting the probabilities of topic sentence, similarity with article title and other sentences, and sentence position as characteristics that affect sentence importance. At this time, a hypothesis is established that the Topic Sentence will have a characteristic distinct from the general sentence, and a deep learning-based classification model is trained to obtain a topic sentence probability value for the input sentence. Also, using the pre-learned ELMo language model, the similarity between sentences is calculated based on the sentence vector value reflecting the context information and extracted as sentence characteristics. The topic sentence classification performance of the LSTM and BERT models was 93% accurate, 96.22% recall, and 89.5% precision, resulting in high analysis results. As a result of calculating the importance of each sentence by combining the extracted sentence characteristics, it was confirmed that the performance of extracting the topic sentence was improved by about 10% compared to the existing TextRank algorithm.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.38-47
• /
• 2021

This study analyzed media reports on the Address of Things, which are being introduced through the amendment of related law and pilot projects. The titles and its texts in the media's reports were collected by searching for 'Address of Things' on the Naver News Platform. Then, we analyzed the corpus using by topic modeling and network analysis. As a result, there were four topics: 'Promotion of the address of things system', Proof of assigning Address of Things', 'Improvement of usage of the Roadname Address Systems', and 'Education and public relation for the address activation'. It was confirmed that the topic 'Proof of assigning Address of Things' was the main agenda. We presented some implication by comparing the results with the 「3rd Basic Plan for Address Policy (2018-2022)」 of the Ministry of Public Administration and Security.

• The Korean Journal of Franchise Management
• /
• v.13 no.4
• /
• pp.1-12
• /
• 2022

Purpose: In 2020, the franchise industry accomplished a significant growth compared to the previous year, as the number of franchise companies increased by 9.0% while the number of franchise brands increased by 12.5%. Despite growth in size, the Korean franchise industry underwent many negative incidents, such as franchise ownership sales to private equity funds, that led to deterioration of businesses. From this point of view, this study aims to make various proposals to help policy makers develop franchise industry policies by analyzing trends of the current and previous presidential administrations' franchise policies and regulations using newspaper articles. Research design, data and methodology: A total of 7,439 articles registered in Naver API from February 25, 2013 to November 29, 2021 were extracted. Among them, 34 unrelated video articles were deleted, and a total of 7,405 articles from both administrations were used for analysis. The R package was used for word frequency analysis, word clouding, word correlation analysis, and LDA (Latent Dirichlet Allocation) topic modeling. Results: The keyword frequency analysis shows that the most frequently mentioned keywords during the previous administration include 'no-brand', 'major company', 'bill', 'business field', and 'SMEs', and those mentioned during the current administration include 'industry' and 'policy'. As a result of LDA topic modeling, 9 topics such as 'global startups' and 'job creation' from the previous administration, and 10 topics such as 'franchise business' and 'distribution industry' from the current administration were derived. The results of LDAvis showed that the previous administration operated a policy based on mutual growth of large and small businesses rather than hostile regulations in the franchise business, whereas the current administration extended the regulation related to franchise business to the employment sector. Conclusions: The analysis of past two administrations' franchise policy, it can be suggested that franchisors and franchisees may complement each other in developing the Fair Transactions in Franchise Business Act and achieving balanced growth. Moreover, political support is needed for sound development of franchisors. Limitations and future research suggestions are presented at the end of this study.

• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1138-1148
• /
• 2017

Topic extraction is a technology that automatically extracts a set of topics from a set of documents, and this has been a major research topic in the area of natural language processing. Representative topic extraction methods include Latent Dirichlet Allocation (LDA) and word clustering-based methods. However, there are problems with these methods, such as repeated topics and mixed topics. The problem of repeated topics is one in which a specific topic is extracted as several topics, while the problem of mixed topic is one in which several topics are mixed in a single extracted topic. To solve these problems, this study proposes a method to extract topics using an LDA that is robust against the problem of repeated topic, going through the steps of separating and merging the topics using the similarity between words to correct the extracted topics. As a result of the experiment, the proposed method showed better performance than the conventional LDA method.