• The Journal of Society for e-Business Studies
• /
• v.14 no.4
• /
• pp.59-73
• /
• 2009

Keyword extraction is an important and essential technique for text mining applications such as information retrieval, text categorization, summarization and topic detection. A set of keywords extracted from a large-scale electronic document data are used for significant features for text mining algorithms and they contribute to improve the performance of document browsing, topic detection, and automated text classification. This paper presents a keyword extraction technique that can be used to detect topics for each news domain from a large document collection of internet news portal sites. Basically, we have used six variants of traditional TF-IDF weighting model. On top of the TF-IDF model, we propose a word filtering technique called 'cross-domain comparison filtering'. To prove effectiveness of our method, we have analyzed usefulness of keywords extracted from Korean news articles and have presented changes of the keywords over time of each news domain.

• 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.

• Journal of Agricultural Extension & Community Development
• /
• v.3 no.1
• /
• pp.141-155
• /
• 1996

The purpose of this study was to investigate the sole of local newspaper for community development in Korea. Specific objectives of the study were : 1) to identify the role of local newspaper in community development, 2) to analyze problems and situations on local newspapers in Korea, and 3) to suggest desirable roles of local newspaper for the community development. To attain the above objectives, this study was carried out through literature review, contest analysis of selected local newspapers, and the questionnaire survey of selected readers of local newspaper. The data were collected from 267 readers of local newspaper who participated in the farmers` training session in the Rural Development Administration, by using questionnaires developed by the researcher, and total of 263 questionnaires were analyzed. The statistical techniques used for the study were frequence, percentile, standard deviation utilizing the $SPSS/PC^+$. The major findings of the study were as follows : 1. The major roles of functions of local newspapers identified in this study were summarized as to reinforce the community consciousness, to form community opinion, to watch and to monitor community environment, to provide education and entertainment, and to contribute to the conveyance and promotion of community culture. 2. The general characteristic of local newspaper readers surveyed were; a) average distance from town to their village was 9.3 Km, b) average age was 29 years, c) about 75% of them were senior high school graduates, and d) about 96% of them participated in group activities. 3. About 45% of the respondents used television or radio for their moor sources of local news were TV or radio, while about 31% respondents used immunity newspaper for their moor sources of local news. About 67% of the respondents kept their readership over two years, and about 40% of them read community newspaper regularly at their home. 4. The results of content analysis showed drat the local newspapers were dealing with articles on cultural affairs, community consciousness, administrative and civic affairs, however, there were not enough educational news, and various kinds of general news in the community. 5. Survey also showed the most needed news were ; 1) political news including administrative and civic affairs, 2) economic news including sales and distribution, 3) social news including social problems on environmental pollution and community development works, 4) educational news including technology and information, 5) cultural news including guide to cultural and historical sites and local brief news. 6. In the evaluation of local newspaper, the readers were generally positive in valued roles of local newspaper in community relations, community development, promoting community cohesion and understanding of community members, and about 40% of the respondents were positive in predicting the bright future perspectives of local newspapers. 7. In the readers` evaluation of local newspaper, readers responded that local newspapers were very closely related to the community and residents, reflecting the current concerns of local population and recognizing the value of community media, and the contents of local newspaper were positively related to daily lives of community residents and opinions of overall community.

• Korean journal of communication and information
• /
• v.61
• /
• pp.5-27
• /
• 2013

Media coverage of depression, the mental disorder, is on the high rise following the soaring number of reported celebrity suicide. This study is an exploratory attempt to get a glance on how online news media are portraying depression. The content analysis results indicate that celebrity was the most cited source, outnumbering the others such as non-celebrity patients and experts. More than half of the sample attributed the cause of depression to socio-psychological factors. Medical consultation was the most reported means of treating depression among the sample, while over the half did not suggest any treatment methods at all. Overall, celebrity related news were less likely to talk about the cause and treatment methods. In addition, the more neuro-biological factors were designated as the main cause of depression in the articles, the more chances of treatment method of all kinds were brought up. The frame of human interest dominated a little less than half of the articles examined, and only few reported positive outcome or achievements after coping with depression.

• Journal of KIISE:Software and Applications
• /
• v.33 no.6
• /
• pp.564-573
• /
• 2006

Temporal information plays an important role in natural language processing (NLP) applications such as information extraction, discourse analysis, automatic summarization, and question-answering. In the topic detection and tracking (TDT) area, the temporal information often used is the publication date of a message, which is readily available but limited in its usefulness. We developed a relatively simple NLP method of extracting temporal information from Korean news articles, with the goal of improving performance of TDT tasks. To extract temporal information, we make use of finite state automata and a lexicon containing time-revealing vocabulary. Extracted information is converted into a canonicalized representation of a time point or a time duration. We first evaluated the extraction and canonicalization methods for their accuracy and investigated on the extent to which temporal information extracted as such can help TDT tasks. The experimental results show that time information extracted from text indeed helps improve both precision and recall significantly.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.99-107
• /
• 2024

In an environment where computer-related technologies are rapidly changing, cyber threats continue to emerge as they are advanced and diversified along with new technologies. Therefore, in this study, we would like to collect security-related news articles, conduct LDA topic modeling, and examine trends. To that end, news articles from January 2020 to August 2023 were collected and major topics were derived through LDA analysis. After that, the flow by topic was grasped and the main origin was analyzed. The analysis results show that ransomware attacks in 2021 and hacking of virtual asset exchanges in 2023 are major issues in the recent security sector. This allows you to check trends in security issues and see what research should be focused on in the future. It is also expected to be able to recognize the latest threats and support appropriate response strategies, contributing to the development of effective security measures.

• Smart Media Journal
• /
• v.13 no.9
• /
• pp.9-17
• /
• 2024

This study aims to analyze the current status of smart tourism in various regions. To achieve this, 599 news articles containing the keyword 'smart tourism' were collected from national daily newspapers in the BigKinds database, covering the period from January 2014 to June 2024. The collected data was subject to topic modeling based on location, and network analysis was performed using the keyword frequencies in each topic. The topic modeling results identified six major topics: 'Jeju,' 'Incheon,' 'Daegu_Busan_Ulsan,' 'Gyeongju,' 'Suwon,' and 'Yangyang.' It was found that the development of smart tourism in all these regions is centered around tourism projects led by government and local authorities. The network analysis results revealed that 'platform' and 'content' are key keywords related to smart tourism technology across all topics, indicating that these concepts are interconnected to provide services to individual tourists. The findings of this study are expected to provide valuable information for formulating policies and strategies to promote smart tourism in various regions and contribute to the realization of sustainable smart tourism.

• Korean journal of communication and information
• /
• v.57
• /
• pp.202-226
• /
• 2012

The purpose of this study is to analyze how Chinese people perceive the acceptance and spread of Korean popular culture through the analysis of the Korean Wave news frame in Chinese daily newspapers. The result of analysis showed that there was a significant difference in the number of an article appearance in all three daily newspapers by year according to a specific issue including the popularity of Korean Wave-related events, Korean dramas, movies and Korean stars. This reporting trend also appeared in the article format, and all three daily newspapers mainly used an episodic frame to deliver fragmentary Korean Wave trend or personal information emotionally rather than a thematic frame to analyze and interpret the Korean Wave trend in depth. As a result of analyzing dominant news frames using the inductive approach to examine specific contents of the articles, news frames that composed the Korean Wave into the cultural interest frame as 'Interest and attention toward Korean popular culture' and gave positive evaluations were dominant, followed by the economic news frames that explained the Korean Wave from the economic perspective and the political news frames that considered the Korean Wave from the viewpoint of the Chinese Government. These news frames appeared somewhat different according to the publishing purpose of daily newspapers. ${\ll}$People's Daily${\gg}$ which is the official organ of the Chinese Communist Party often covered the political frames to report the policies of Chinese government, ${\ll}$People's Daily (Overseas edition)${\gg}$ often covered economic frames from the overseas perspective and the Jinghua Daily which is a commercial newspaper by nature often handled cultural interest frames to consider Korean Wave as new cultural phenomenon.

• Korean journal of communication and information
• /
• v.39
• /
• pp.40-68
• /
• 2007

Despite many efforts to improve water and publicize Arisu, ordinary citizens' distrust in water is still intense. This study aims to analyze how newspapers, television and internet media in Korea covered water-related news, focusing on the type of articles, themes, news sources, and news values. As a result, the mostly mentioned theme in the media was the discussion about suitability of water as a drinking water, followed by impurified water, governmental policy on water, coverage on the water pipe, and result of examination of water quality. Also among newspapers, broadcasting, and the internet, the internet medium showed the most negative tone in covering water. Stories written by journalists with expertise were less than 1% whereas stories by ordinary journalists were mostly found. In conclusion, to cover public issues like water desirably, it is necessary to bring up journalists with expertise in environmental issues, to diversify news sources, and to do investigative reporting rather than reporting appealing to audience's amusement.

• The Research Journal of the Costume Culture
• /
• v.30 no.1
• /
• pp.102-120
• /
• 2022

With the growing importance of ESG as a must-have business strategy, this study attempted to analyze the current state of ESG practices in the Korean fashion businesses. The ESG cases of fashion business were collected from news articles searched on the largest Korean internet portal by November 2021 from October 2020 when the number of articles began to increase meaningfully. Three hundred ninety one ESG cases of 112 fashion manufacturing brands and 332 ESG cases of 49 retail brands were analyzed. Casual and outdoor/sportswear brands among fashion manufacturers were most active in ESG practices, and various online and offline retailers were practicing ESG. Approximately one-third of the fashion brands were positioned as eco-friendly concept. While environmental practices were the most practiced ESG, governance was the least practiced. Among environmental practices, fashion manufacturing businesses were most active in eco-friendly product development, while retail businesses were in eco-friendly campaign-event-service and eco-friendly packaging. The most active social practice was the contribution to communities, followed by retail businesses' sharing growth with partner businesses. Governance practices were focused on the structure and operation of the board. Various ESG collaborations with various partners were also observed. The research result is meaningful verifying and diagnosing the ESG practices of the Korean fashion businesses.