• Journal of Information Processing Systems
• /
• v.17 no.6
• /
• pp.1057-1070
• /
• 2021

Case-related news filtering is crucial in legal text mining and divides news into case-related and case-unrelated categories. Because case-related news originates from various fields and has different writing styles, it is difficult to establish complete filtering rules or keywords for data collection. In addition, the labeled corpus for case-related news is sparse; therefore, to train a high-performance classification model, it is necessary to annotate the corpus. To address this challenge, we propose topic-enhanced positive-unlabeled learning, which selects positive and negative samples guided by topics. Specifically, a topic model based on a variational autoencoder (VAE) is trained to extract topics from unlabeled samples. By using these topics in the iterative process of positive-unlabeled (PU) learning, the accuracy of identifying case-related news can be improved. From the experimental results, it can be observed that the F1 value of our method on the test set is 1.8% higher than that of the PU learning baseline model. In addition, our method is more robust with low initial samples and high iterations, and compared with advanced PU learning baselines such as nnPU and I-PU, we obtain a 1.1% higher F1 value, which indicates that our method can effectively identify case-related news.

• The Journal of Information Systems
• /
• v.30 no.4
• /
• pp.303-327
• /
• 2021

Purpose The online comments on news content have become social information and are understood based on deliberative democracy. Although the related research has focused on the relationship between online comments and their deliberative quality, the social information provided by online comments consists of not only direct information such as comments themselves but also indirect information such as 'likes' and 'dislikes'. Therefore, the research on online comments and deliberative quality should study this direct and indirect information together, and the direction and the degree of the indirect information should be also considered with them. Design/methodology/approach This study distinguishes comments by the attached 'likes' and 'dislikes', identifies highly supported and highly unsupported comments by the intensity of 'likes' and 'dislikes', and investigates the relationship between their existence and the deliberative quality measured as the topic diversity. Then, we applied topic modeling to the 2,390 news articles and their 74,385 comments collected from five news sites. Findings The topic diversities of the supported and unsupported comments are related to the topic diversity of all comments but the degree of the relationship is higher in the case of supported comments. Furthermore, the existence of highly supported and unsupported comments is led to less diversity of all comments compared to the case where those comments are absent. Particularly, when only highly supported comments are present, topic diversity was lower than in the opposite case.

• The Journal of the Korea Contents Association
• /
• v.18 no.10
• /
• pp.53-64
• /
• 2018

This study analyzed contents of main news of 7 channels for 4 years during the initial period of introduction of the general programming cable channel(GPCC) in order to examine changes in subject composition and diversity of broadcasting news contents due to the introduction of GPCC. As a result of the analysis, terrestrial broadcasters treated a wide range of topics, while the GPCC's news focused on political news and differentiated from the terrestrial in the composition of the topic. In the composition of the news topic headline news, GPCC showed distinctive structure using political news and North Korea news, while terrestrial news was treated as major news for economic and daily information news. As a result of analyzing the diversity of broadcast news in the first four years of opening GPCC, it has changed into a strategy of selecting and concentrating in order to compete with the terrestrial broadcasters. In the initial broadcasting news market, the terrestrial broadcastings were used to maintain diversity strategies while the GPCCs were using concentrated strategies.

• Journal of Digital Convergence
• /
• v.19 no.11
• /
• pp.575-583
• /
• 2021

This study aims to analyze Taekwondo trends according to news articles by year by applying topic modeling. In order to examine the Taekwondo trend through media reports, articles including news articles and Taekwondo specialized media articles were collected through Big Kinds of the Korea Press Foundation. The search period was divided into three sections: before 2000, 2001~2010, and 2011~2020. A total of 12,124 items were selected as research data. For topic analysis, pre-processing was performed, and topic analysis was performed using the LDA algorithm. In this case, python 3 was applied for all analysis. First, as a result of analyzing the topics of media articles by year, 'World' was the most common keyword before 2000. 'South and North Korea' was next common and 'Olympic' was the third commonest topic. From 2001 to 2010, 'World' was the most common topic, followed by 'Association' and 'World Taekwondo'. From 2011 to 2020, 'World', 'Demonstration', and 'Kukkiwon' was the most common topic in that order. Second, as a result of analyzing news articles before 2000 by topic modeling, topics were divided into two categories. Specifically, Topic 1 was selected as 'South-North Korea sports exchange' and Topic 2 was selected as 'Adoption of Olympic demonstration events'. Third, as a result of analyzing news articles from 2001 to 2010 by topic modeling, three topics were selected. Topic 1 was selected as 'Taekwondo Demonstration Performance and Corruption', Topic 2 was selected as 'Muju Taekwondo Park Creation', and Topic 3 was selected as 'World Taekwondo Festival'. Fourth, as a result of analyzing news articles from 2011 to 2020 by topic modeling, three topics were selected. Topic 1 was selected as 'Successful Hosting of the 2018 Pyeongchang Winter Olympics', Topic 2 was selected as 'North-South Korea Taekwondo Joint Demonstration Performance', and Topic 3 was selected as '2017 Muju World Taekwondo Championships'.

• 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 the Korea Academia-Industrial cooperation Society
• /
• v.19 no.10
• /
• pp.176-182
• /
• 2018

In order to understand and track the trends of construction safety accident, this study shows the topic trends in the construction safety accident with LDA(Latent Dirichlet Allocation)-based topic modeling method for data analytics. Especially, it performs to figure out the main issue of construction safety accident with unstructured data analysis based on the topic modeling rather than a variety of structured data analysis for preventing to safety accident in construction industry. To apply this methodology, I randomly collected to 540 news article data about construction accident from January 2017 to February 2018. Based on the unstructured data with the LDA-based topic modeling, I found the 10 topics and identified key issues through 10 keyword in each 10 topics. I forecasted the topic issue related to construction safety accident based on analysis of time-series trends about the news data from January 2017 to February 2018. With this method, this research gives a hint about ways of using unstructured news article data to anticipate safety policy and research field and to respond to construction accident safety issues in the future.

• Journal of Computing Science and Engineering
• /
• v.10 no.4
• /
• pp.128-136
• /
• 2016

It is impossible for any human being to analyze the more than 500 million tweets that are generated per day. Lexical ambiguities on Twitter make it difficult to retrieve the desired data and relevant topics. Most of the solutions for the word sense disambiguation problem rely on knowledge base systems. Unfortunately, it is expensive and time-consuming to manually create a knowledge base system, resulting in a knowledge acquisition bottleneck. To solve the knowledge-acquisition bottleneck, a topic signature is used to disambiguate words. In this paper, we evaluate the effectiveness of various features of newspapers on the topic signature extraction for word sense discrimination in tweets. Based on our results, topic signatures obtained from a snippet feature exhibit higher accuracy in discriminating company names than those from the article body. We conclude that topic signatures extracted from news articles improve the accuracy of word sense discrimination in the automated analysis of tweets.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.11
• /
• pp.1751-1754
• /
• 2022

The news articles collected with keyword "non face-to-face" were analyzed through topic modeling applied with LDA algorithm. In this study, collected articles were divided into two periods, period 1(the beginning of COVID-19 spread) and period 2(the end of COVID-19 spread), according to issued date of the articles. The articles of period 1 showed support for non-face-to-face treatment, smart library, the beginning of the online financial era, non-face-to-face entrance exam and employment, stock investment for main topic words. And the articles of period 2 showed conversion to non face-to-face classes, increasing unmanned stores, online finance, education industry, home treatment for main topic words. Also, further issues were discussed through visualization of topic words. These results provide evidence that education and unmanned business in non-face-to-face industries are growing.

• Korea Trade Review
• /
• v.46 no.4
• /
• pp.61-76
• /
• 2021

This study focuses on three logistics-related news (Logistics Newspaper, Korea Shipping Gadget, and Korea Shipping Newspaper) in order to present changes in logistics issues, centering on Corona 19, which has recently had the greatest impact in the world. For data collection, two-year news articles in 2019 and 2020 (title, article, content, date, article classification, article URL) were collected through web crawling (using Python's BeautifulSoup, requests module) on the homepages of three representative logistics-related media companies. As for the data analysis methods, fundamental statistical analysis, Latent Dirichlet Allocation (LDA) for topic modeling, and Scattertext were performed. The analysis results were as follows. First, among the three news media related to logistics, the Korea Shipping Newspaper was carrying out the most active media activities. Second, through topic modeling with LDA, eight logistics-related topics were identified, and keywords and significant issues of each topic were presented. Third, the keywords were visually expressed through Scattertext. This is the first study to present changes in the logistics field, focusing on articles from representative logistics-related media in 2019 and 2020. In particular, 2019 and 2020 can be divided into before and after the outbreak of Corona 19, which has had a great impact not only on the logistics field but also on our lives as a whole. For future work, a multi-faceted approach is required, such as comparative studies of logistics issues between countries or presenting implications based on long-term time-series articles.

• Journal of Digital Convergence
• /
• v.18 no.9
• /
• pp.17-27
• /
• 2020

News articles and blog posts have influence on social agenda setting and this study applied text mining on the subject of solar PV in rural area appeared in those media. Texts are gained from online news articles and blog posts with rural solar PV as a keyword by web scrapping, and these are analysed by sentiment analysis and topic modeling technique. Sentiment analysis shows that the proportion of negative texts are significantly lower in blog posts compared to news articles. Result of topic modeling shows that topics related to government policy have the largest loading in positive articles whereas various topics are relatively evenly distributed in negative articles. For blog posts, topics related to rural area installation and environmental damage are have the largest loading in positive and negative texts, respectively. This research reveals issues related to rural solar PV by combining sentiment analysis and topic modeling that were separately applied in previous studies.